Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d1a11bb6ba098907d7444e19cb585d94acb153e1cbdfae3564b5288e10be81e
+oid sha256:53b2d1a8e9ca4c511cdc1e6fee9b93ac287908b72c782ba2512d94a16d0bef87
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31003d79c4ad77e9654c4420804428087793290349c7b62a58323447c092eedc
+oid sha256:7a8a35651c1e0f486544d82912d9abd79f21b1d8e3e3a31b0a54ca9430b9f8a9
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8f4cd27f1868d83f3fdb16d5d64a2f27bbe41bb0197aaa9a0bc2e9c7bbe9aa4
+oid sha256:d1aefd6b5cb7ab5293be3b57c5a81d7e2a62b44d9e7b6cc213897ed1dd28dec5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021196095679175894,
+  "epoch": 0.004239219135835179,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 1.6203,
       "step": 25
+    },
+    {
+      "epoch": 0.0022043939506342933,
+      "grad_norm": 5.318032264709473,
+      "learning_rate": 0.0001,
+      "loss": 1.2805,
+      "step": 26
+    },
+    {
+      "epoch": 0.0022891783333509968,
+      "grad_norm": 6.56615686416626,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.7687,
+      "step": 27
+    },
+    {
+      "epoch": 0.0023739627160677002,
+      "grad_norm": 6.601612091064453,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.9514,
+      "step": 28
+    },
+    {
+      "epoch": 0.002458747098784404,
+      "grad_norm": 8.648096084594727,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.7966,
+      "step": 29
+    },
+    {
+      "epoch": 0.0025435314815011076,
+      "grad_norm": 9.545267105102539,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.7292,
+      "step": 30
+    },
+    {
+      "epoch": 0.002628315864217811,
+      "grad_norm": 7.909492015838623,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.9538,
+      "step": 31
+    },
+    {
+      "epoch": 0.0027131002469345145,
+      "grad_norm": 6.8322367668151855,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.1442,
+      "step": 32
+    },
+    {
+      "epoch": 0.0027978846296512184,
+      "grad_norm": 6.240336894989014,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.9339,
+      "step": 33
+    },
+    {
+      "epoch": 0.002882669012367922,
+      "grad_norm": 8.01297378540039,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.525,
+      "step": 34
+    },
+    {
+      "epoch": 0.0029674533950846253,
+      "grad_norm": 8.416840553283691,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.7266,
+      "step": 35
+    },
+    {
+      "epoch": 0.003052237777801329,
+      "grad_norm": 6.560504913330078,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.9834,
+      "step": 36
+    },
+    {
+      "epoch": 0.0031370221605180326,
+      "grad_norm": 6.503190994262695,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.364,
+      "step": 37
+    },
+    {
+      "epoch": 0.003221806543234736,
+      "grad_norm": 8.527243614196777,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.5102,
+      "step": 38
+    },
+    {
+      "epoch": 0.0033065909259514395,
+      "grad_norm": 8.381340026855469,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.4996,
+      "step": 39
+    },
+    {
+      "epoch": 0.0033913753086681434,
+      "grad_norm": 10.311125755310059,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.665,
+      "step": 40
+    },
+    {
+      "epoch": 0.003476159691384847,
+      "grad_norm": 7.071728229522705,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.5634,
+      "step": 41
+    },
+    {
+      "epoch": 0.0035609440741015503,
+      "grad_norm": 6.2012248039245605,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.1765,
+      "step": 42
+    },
+    {
+      "epoch": 0.0036457284568182542,
+      "grad_norm": 6.488067150115967,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.1878,
+      "step": 43
+    },
+    {
+      "epoch": 0.0037305128395349577,
+      "grad_norm": 6.788881778717041,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.7673,
+      "step": 44
+    },
+    {
+      "epoch": 0.003815297222251661,
+      "grad_norm": 8.740360260009766,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.7525,
+      "step": 45
+    },
+    {
+      "epoch": 0.003900081604968365,
+      "grad_norm": 6.092394828796387,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.408,
+      "step": 46
+    },
+    {
+      "epoch": 0.003984865987685068,
+      "grad_norm": 6.857183456420898,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.9187,
+      "step": 47
+    },
+    {
+      "epoch": 0.004069650370401772,
+      "grad_norm": 6.588223457336426,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.0684,
+      "step": 48
+    },
+    {
+      "epoch": 0.004154434753118476,
+      "grad_norm": 6.943943977355957,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.6099,
+      "step": 49
+    },
+    {
+      "epoch": 0.004239219135835179,
+      "grad_norm": 8.967212677001953,
+      "learning_rate": 0.0,
+      "loss": 1.7563,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.70950084231168e+16,
+  "total_flos": 7.41900168462336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null