Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141a3d08ad3daa4d04b8e5ee7abd899d14cd6285f8a15cb568df5659e03e6179
+oid sha256:42ddf48b08b551c472100934e25e2af688e2c64d7b9e4b74735648f82a4620b0
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa418d59d4133abd14f1c202fbe4b0ff2e7746c79f83cf9328e9cff3d631742
+oid sha256:2b622ae5db7f3113cc310b4a78b540b1e11908ed2f6c42008c28f6f6af35cc7c
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b69a2a81b40ab5e6b9ba2c34553cf94b7b224252152903292ade9a382e01763
+oid sha256:38080fcfd318203580ba6b2067b21801392a0daaf352eadebc489ee3a46f9b04
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02449779519843214,
+  "epoch": 0.03266372693124286,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 1.2616,
       "step": 75
+    },
+    {
+      "epoch": 0.02482443246774457,
+      "grad_norm": 1.1292190551757812,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1895,
+      "step": 76
+    },
+    {
+      "epoch": 0.025151069737056997,
+      "grad_norm": 1.174579381942749,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4004,
+      "step": 77
+    },
+    {
+      "epoch": 0.025477707006369428,
+      "grad_norm": 1.012466549873352,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2333,
+      "step": 78
+    },
+    {
+      "epoch": 0.025804344275681856,
+      "grad_norm": 0.7937297821044922,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1496,
+      "step": 79
+    },
+    {
+      "epoch": 0.026130981544994283,
+      "grad_norm": 0.9715169072151184,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2848,
+      "step": 80
+    },
+    {
+      "epoch": 0.02645761881430671,
+      "grad_norm": 1.2033419609069824,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.3095,
+      "step": 81
+    },
+    {
+      "epoch": 0.02645761881430671,
+      "eval_loss": 1.3124163150787354,
+      "eval_runtime": 130.6427,
+      "eval_samples_per_second": 19.733,
+      "eval_steps_per_second": 2.472,
+      "step": 81
+    },
+    {
+      "epoch": 0.026784256083619142,
+      "grad_norm": 1.259170413017273,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3473,
+      "step": 82
+    },
+    {
+      "epoch": 0.02711089335293157,
+      "grad_norm": 1.0674095153808594,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.3123,
+      "step": 83
+    },
+    {
+      "epoch": 0.027437530622243998,
+      "grad_norm": 1.047490119934082,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.2067,
+      "step": 84
+    },
+    {
+      "epoch": 0.027764167891556425,
+      "grad_norm": 0.9544463753700256,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3305,
+      "step": 85
+    },
+    {
+      "epoch": 0.028090805160868856,
+      "grad_norm": 1.324135422706604,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.4236,
+      "step": 86
+    },
+    {
+      "epoch": 0.028417442430181284,
+      "grad_norm": 1.158332347869873,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.4892,
+      "step": 87
+    },
+    {
+      "epoch": 0.02874407969949371,
+      "grad_norm": 1.1442019939422607,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.3119,
+      "step": 88
+    },
+    {
+      "epoch": 0.02907071696880614,
+      "grad_norm": 1.0604044198989868,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.2898,
+      "step": 89
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "grad_norm": 1.0450000762939453,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.3608,
+      "step": 90
+    },
+    {
+      "epoch": 0.02939735423811857,
+      "eval_loss": 1.3116309642791748,
+      "eval_runtime": 131.1104,
+      "eval_samples_per_second": 19.663,
+      "eval_steps_per_second": 2.464,
+      "step": 90
+    },
+    {
+      "epoch": 0.029723991507430998,
+      "grad_norm": 1.0420557260513306,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.1929,
+      "step": 91
+    },
+    {
+      "epoch": 0.030050628776743426,
+      "grad_norm": 0.983333945274353,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.2359,
+      "step": 92
+    },
+    {
+      "epoch": 0.030377266046055854,
+      "grad_norm": 0.8582541346549988,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.1846,
+      "step": 93
+    },
+    {
+      "epoch": 0.030703903315368285,
+      "grad_norm": 1.0503182411193848,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.1297,
+      "step": 94
+    },
+    {
+      "epoch": 0.031030540584680712,
+      "grad_norm": 1.3140679597854614,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4957,
+      "step": 95
+    },
+    {
+      "epoch": 0.03135717785399314,
+      "grad_norm": 1.139602780342102,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.283,
+      "step": 96
+    },
+    {
+      "epoch": 0.03168381512330557,
+      "grad_norm": 1.0372895002365112,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.2945,
+      "step": 97
+    },
+    {
+      "epoch": 0.032010452392617995,
+      "grad_norm": 1.088069200515747,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.3078,
+      "step": 98
+    },
+    {
+      "epoch": 0.03233708966193043,
+      "grad_norm": 0.9816431403160095,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.3681,
+      "step": 99
+    },
+    {
+      "epoch": 0.03233708966193043,
+      "eval_loss": 1.3114665746688843,
+      "eval_runtime": 131.0706,
+      "eval_samples_per_second": 19.669,
+      "eval_steps_per_second": 2.464,
+      "step": 99
+    },
+    {
+      "epoch": 0.03266372693124286,
+      "grad_norm": 0.9700720906257629,
+      "learning_rate": 0.0,
+      "loss": 1.3082,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47566301806592e+16,
+  "total_flos": 1.96755069075456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null