Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794bed3415be79d8a164a34b2d4810fc31fc907565dbded7aefdea8663335e3f
+oid sha256:9bd6331a37bb305f0f7abcf2d60cf80771f7e6d49eb3cbfe1317ffa3f68b6168
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9a2b8bea77598f49595ebb8d3e9bf3c0bb9206e61bfe244fe61650bb9e87c6
+oid sha256:b5eb6988b836540ce571449c0e21fddde6ee497c8c1a0c530aec149f79f7b299
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
+oid sha256:2641fe94f6f5285a893d26b6a83b6bc1718c94cdba5b09f9fe77818d5a69d3a2
 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": 0.22522522522522523,
+  "epoch": 0.3003003003003003,
   "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": 1.0725,
       "step": 75
+    },
+    {
+      "epoch": 0.22822822822822822,
+      "grad_norm": 0.5668699145317078,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.0711,
+      "step": 76
+    },
+    {
+      "epoch": 0.23123123123123124,
+      "grad_norm": 0.5445249676704407,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.0106,
+      "step": 77
+    },
+    {
+      "epoch": 0.23423423423423423,
+      "grad_norm": 0.6580765843391418,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.08,
+      "step": 78
+    },
+    {
+      "epoch": 0.23723723723723725,
+      "grad_norm": 0.5185084939002991,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0145,
+      "step": 79
+    },
+    {
+      "epoch": 0.24024024024024024,
+      "grad_norm": 0.6230930089950562,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.0017,
+      "step": 80
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 0.5382445454597473,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.0962,
+      "step": 81
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "eval_loss": 1.0725353956222534,
+      "eval_runtime": 62.8805,
+      "eval_samples_per_second": 4.469,
+      "eval_steps_per_second": 0.573,
+      "step": 81
+    },
+    {
+      "epoch": 0.24624624624624625,
+      "grad_norm": 0.5744390487670898,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0982,
+      "step": 82
+    },
+    {
+      "epoch": 0.24924924924924924,
+      "grad_norm": 0.5682293176651001,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0377,
+      "step": 83
+    },
+    {
+      "epoch": 0.25225225225225223,
+      "grad_norm": 0.5965850949287415,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.0009,
+      "step": 84
+    },
+    {
+      "epoch": 0.2552552552552553,
+      "grad_norm": 0.47231999039649963,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0434,
+      "step": 85
+    },
+    {
+      "epoch": 0.25825825825825827,
+      "grad_norm": 0.5315771698951721,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.9827,
+      "step": 86
+    },
+    {
+      "epoch": 0.26126126126126126,
+      "grad_norm": 0.5202770829200745,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.0421,
+      "step": 87
+    },
+    {
+      "epoch": 0.26426426426426425,
+      "grad_norm": 0.551384449005127,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1419,
+      "step": 88
+    },
+    {
+      "epoch": 0.2672672672672673,
+      "grad_norm": 0.48965591192245483,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.0447,
+      "step": 89
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.5531151294708252,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0893,
+      "step": 90
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "eval_loss": 1.0678226947784424,
+      "eval_runtime": 62.7776,
+      "eval_samples_per_second": 4.476,
+      "eval_steps_per_second": 0.573,
+      "step": 90
+    },
+    {
+      "epoch": 0.2732732732732733,
+      "grad_norm": 0.4997876286506653,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.0278,
+      "step": 91
+    },
+    {
+      "epoch": 0.27627627627627627,
+      "grad_norm": 0.5054656267166138,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.0288,
+      "step": 92
+    },
+    {
+      "epoch": 0.27927927927927926,
+      "grad_norm": 0.5292591452598572,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.9494,
+      "step": 93
+    },
+    {
+      "epoch": 0.2822822822822823,
+      "grad_norm": 0.47419047355651855,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.9839,
+      "step": 94
+    },
+    {
+      "epoch": 0.2852852852852853,
+      "grad_norm": 0.49080803990364075,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.0356,
+      "step": 95
+    },
+    {
+      "epoch": 0.2882882882882883,
+      "grad_norm": 0.5078819990158081,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1231,
+      "step": 96
+    },
+    {
+      "epoch": 0.2912912912912913,
+      "grad_norm": 0.4944559931755066,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.0759,
+      "step": 97
+    },
+    {
+      "epoch": 0.29429429429429427,
+      "grad_norm": 0.4932954013347626,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.0656,
+      "step": 98
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 0.4978138208389282,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0526,
+      "step": 99
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "eval_loss": 1.066880702972412,
+      "eval_runtime": 62.8204,
+      "eval_samples_per_second": 4.473,
+      "eval_steps_per_second": 0.573,
+      "step": 99
+    },
+    {
+      "epoch": 0.3003003003003003,
+      "grad_norm": 0.47974127531051636,
+      "learning_rate": 0.0,
+      "loss": 1.0622,
+      "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": 1.112830925340672e+17,
+  "total_flos": 1.483774567120896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null