Training in progress, epoch 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29ac7ba6f53f92462f92ab317dac22f616978288aa0a0bf5eb7b73a93e8623b
+oid sha256:ff84ff1b2afe3c81648f69c662425e5133939e807416e00c8d1b88dd05b828ee
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a7f4d414d1b3ef9f1439d2a5c336e25a673350c1f7c1a36bae8691277656ef
+oid sha256:10e34e4100b5f60fc0bc15eaee4d6276d4e620ba5bfdf7a6a550ec8399c77cd5
 size 49846644

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34c69f6d6c32635ff50b0a1faed18792675796ed61b4917357f7fa723205e2f
+oid sha256:aed20ba68feaa8e3d536e2039713340ed613cdb4247d843b649089065ce841e9
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f00b65fe360af6cac79aca5d512b7d43a8aea8109a2419986cb6ec4493d90572
+oid sha256:4f095da1de3720c4e8b58cb81dca9e1af4e0f6355ea16173b6c815307c3df5b3
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3338a4e0a24655344a2e4fe71d8047a4351bfcfb4de0042932ed9ef74e6a9a04
+oid sha256:b17c7c306ef73d802004550d50a4263de1aea4f38798606e532d283cc52d5499
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28ffcb98b6e03917e67aa0d155cd2bcb5bba7adff5ab9f65b2a312750f07526
+oid sha256:336df95e2b6b6d4f80034891f2f2867ce34241dc9a53efc7bdcba0fceba4bb0f
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f34acd8813d6b9c98be80489c6f644fc7604245d4167815c19292650ca21464
+oid sha256:96e143ad827376f99ce0dd7da519bd5666cb85c9dfcd6fffd79ebe3195919c83
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359fcea393c9e357ac9329090b6808db28e869fcad41f7d4e9d5f4ea556aac70
+oid sha256:c5725c1870961018862c368a373dab7c0f2aedede8c986506b38291d26b170bc
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9ec9b30c1aa25c7c28c666461ba2a0d9c5781d925d9a3f624531498737156b1
+oid sha256:63227904d9c4715c227588ec3c511ae61e475d692c6bb4f2db8cc9e3a7643d3f
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b73a0419b8ce412c9ab0e7b0fff0b7e12dd9a30c2645954ee9b29ede96197d8
+oid sha256:7f5b6ebc45a3c99a84ff77360ea3679108eed2a18f52093642827fbeac96f83d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3b5e41a3049ed9c6f775655d186804bf7846bdec4fbbd638a092baab2602b8a
+oid sha256:b4ac31dcfba988823188c44099086577dd09e162577217892c3f4fd5ad8489c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.99812382739212,
+  "epoch": 5.25328330206379,
   "eval_steps": 500,
-  "global_step": 666,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4669,6 +4669,244 @@
       "learning_rate": 1.59624359510657e-06,
       "loss": 0.8788,
       "step": 666
+    },
+    {
+      "epoch": 5.00562851782364,
+      "grad_norm": 0.5438546538352966,
+      "learning_rate": 1.5039580583678393e-06,
+      "loss": 1.7329,
+      "step": 667
+    },
+    {
+      "epoch": 5.01313320825516,
+      "grad_norm": 0.2500527501106262,
+      "learning_rate": 1.414400255879008e-06,
+      "loss": 1.012,
+      "step": 668
+    },
+    {
+      "epoch": 5.0206378986866795,
+      "grad_norm": 0.2738587558269501,
+      "learning_rate": 1.327572642912468e-06,
+      "loss": 1.1039,
+      "step": 669
+    },
+    {
+      "epoch": 5.028142589118199,
+      "grad_norm": 0.2560110092163086,
+      "learning_rate": 1.2434775998910964e-06,
+      "loss": 1.027,
+      "step": 670
+    },
+    {
+      "epoch": 5.0356472795497185,
+      "grad_norm": 0.2611444890499115,
+      "learning_rate": 1.1621174323229612e-06,
+      "loss": 1.0072,
+      "step": 671
+    },
+    {
+      "epoch": 5.043151969981238,
+      "grad_norm": 0.24755235016345978,
+      "learning_rate": 1.0834943707381784e-06,
+      "loss": 0.9297,
+      "step": 672
+    },
+    {
+      "epoch": 5.050656660412758,
+      "grad_norm": 0.2472180277109146,
+      "learning_rate": 1.0076105706276888e-06,
+      "loss": 0.8869,
+      "step": 673
+    },
+    {
+      "epoch": 5.058161350844277,
+      "grad_norm": 0.2653760313987732,
+      "learning_rate": 9.344681123841967e-07,
+      "loss": 0.8558,
+      "step": 674
+    },
+    {
+      "epoch": 5.065666041275797,
+      "grad_norm": 0.2679085433483124,
+      "learning_rate": 8.640690012451515e-07,
+      "loss": 1.1758,
+      "step": 675
+    },
+    {
+      "epoch": 5.073170731707317,
+      "grad_norm": 0.23908266425132751,
+      "learning_rate": 7.964151672377458e-07,
+      "loss": 0.8884,
+      "step": 676
+    },
+    {
+      "epoch": 5.080675422138837,
+      "grad_norm": 0.2759111225605011,
+      "learning_rate": 7.315084651260009e-07,
+      "loss": 1.1085,
+      "step": 677
+    },
+    {
+      "epoch": 5.088180112570356,
+      "grad_norm": 0.2899288833141327,
+      "learning_rate": 6.69350674359959e-07,
+      "loss": 1.1352,
+      "step": 678
+    },
+    {
+      "epoch": 5.095684803001876,
+      "grad_norm": 0.27089551091194153,
+      "learning_rate": 6.099434990268609e-07,
+      "loss": 0.9914,
+      "step": 679
+    },
+    {
+      "epoch": 5.103189493433396,
+      "grad_norm": 0.29111695289611816,
+      "learning_rate": 5.532885678043977e-07,
+      "loss": 0.971,
+      "step": 680
+    },
+    {
+      "epoch": 5.110694183864916,
+      "grad_norm": 0.2626079022884369,
+      "learning_rate": 4.9938743391615e-07,
+      "loss": 0.9628,
+      "step": 681
+    },
+    {
+      "epoch": 5.118198874296436,
+      "grad_norm": 0.27037861943244934,
+      "learning_rate": 4.482415750889204e-07,
+      "loss": 1.0561,
+      "step": 682
+    },
+    {
+      "epoch": 5.125703564727955,
+      "grad_norm": 0.2747006118297577,
+      "learning_rate": 3.998523935122772e-07,
+      "loss": 1.0828,
+      "step": 683
+    },
+    {
+      "epoch": 5.133208255159475,
+      "grad_norm": 0.2585286498069763,
+      "learning_rate": 3.5422121580005864e-07,
+      "loss": 0.9272,
+      "step": 684
+    },
+    {
+      "epoch": 5.140712945590995,
+      "grad_norm": 0.2688470184803009,
+      "learning_rate": 3.1134929295407564e-07,
+      "loss": 1.0374,
+      "step": 685
+    },
+    {
+      "epoch": 5.1482176360225145,
+      "grad_norm": 0.25770020484924316,
+      "learning_rate": 2.7123780032973235e-07,
+      "loss": 0.9986,
+      "step": 686
+    },
+    {
+      "epoch": 5.1557223264540335,
+      "grad_norm": 0.25769320130348206,
+      "learning_rate": 2.3388783760386601e-07,
+      "loss": 1.0169,
+      "step": 687
+    },
+    {
+      "epoch": 5.163227016885553,
+      "grad_norm": 0.29741230607032776,
+      "learning_rate": 1.9930042874457254e-07,
+      "loss": 1.0703,
+      "step": 688
+    },
+    {
+      "epoch": 5.170731707317073,
+      "grad_norm": 0.2753787636756897,
+      "learning_rate": 1.6747652198313957e-07,
+      "loss": 1.0371,
+      "step": 689
+    },
+    {
+      "epoch": 5.178236397748593,
+      "grad_norm": 0.2647511959075928,
+      "learning_rate": 1.3841698978804285e-07,
+      "loss": 1.0168,
+      "step": 690
+    },
+    {
+      "epoch": 5.185741088180112,
+      "grad_norm": 0.27614572644233704,
+      "learning_rate": 1.1212262884103974e-07,
+      "loss": 1.0725,
+      "step": 691
+    },
+    {
+      "epoch": 5.193245778611632,
+      "grad_norm": 0.2685404121875763,
+      "learning_rate": 8.85941600153033e-08,
+      "loss": 1.0614,
+      "step": 692
+    },
+    {
+      "epoch": 5.200750469043152,
+      "grad_norm": 0.2600098252296448,
+      "learning_rate": 6.783222835572055e-08,
+      "loss": 1.0501,
+      "step": 693
+    },
+    {
+      "epoch": 5.208255159474672,
+      "grad_norm": 0.25625452399253845,
+      "learning_rate": 4.98374030611084e-08,
+      "loss": 0.9857,
+      "step": 694
+    },
+    {
+      "epoch": 5.215759849906191,
+      "grad_norm": 0.26039209961891174,
+      "learning_rate": 3.461017746871675e-08,
+      "loss": 1.017,
+      "step": 695
+    },
+    {
+      "epoch": 5.223264540337711,
+      "grad_norm": 0.2616319954395294,
+      "learning_rate": 2.215096904060454e-08,
+      "loss": 1.0131,
+      "step": 696
+    },
+    {
+      "epoch": 5.230769230769231,
+      "grad_norm": 0.264681875705719,
+      "learning_rate": 1.246011935228064e-08,
+      "loss": 1.0703,
+      "step": 697
+    },
+    {
+      "epoch": 5.238273921200751,
+      "grad_norm": 0.26076602935791016,
+      "learning_rate": 5.537894083273543e-09,
+      "loss": 0.9102,
+      "step": 698
+    },
+    {
+      "epoch": 5.24577861163227,
+      "grad_norm": 0.25187480449676514,
+      "learning_rate": 1.384483009898796e-09,
+      "loss": 0.9244,
+      "step": 699
+    },
+    {
+      "epoch": 5.25328330206379,
+      "grad_norm": 0.2918677031993866,
+      "learning_rate": 0.0,
+      "loss": 1.1823,
+      "step": 700
     }
   ],
   "logging_steps": 1,
@@ -4683,12 +4921,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4625303974966723e+18,
+  "total_flos": 1.5363404536186143e+18,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null