Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c57be7494d63ae7e137406fe19c5b688aabfd88b1c51278850967e28ba307f7
+oid sha256:53ab3c1f96e9bde6f63fd65d64075d0ac9835b3234caec36499b000e473daef9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d5f3d00ed41278afa0a0078ab23bacf4148a39ef68730dfdbe88019eed9b515
+oid sha256:921509f8376366ac8686a044fc6ac1d280c64ce2aa1a884d0e74fb0513077d55
 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": 0.43352601156069365,
+  "epoch": 0.5780346820809249,
   "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": 2.531,
       "step": 75
+    },
+    {
+      "epoch": 0.4393063583815029,
+      "grad_norm": 14.048025131225586,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.4943,
+      "step": 76
+    },
+    {
+      "epoch": 0.44508670520231214,
+      "grad_norm": 14.55485725402832,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.5831,
+      "step": 77
+    },
+    {
+      "epoch": 0.4508670520231214,
+      "grad_norm": 9.47404670715332,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.9441,
+      "step": 78
+    },
+    {
+      "epoch": 0.45664739884393063,
+      "grad_norm": 8.202113151550293,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.12,
+      "step": 79
+    },
+    {
+      "epoch": 0.4624277456647399,
+      "grad_norm": 8.428282737731934,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.413,
+      "step": 80
+    },
+    {
+      "epoch": 0.4682080924855491,
+      "grad_norm": 19.201919555664062,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 3.3535,
+      "step": 81
+    },
+    {
+      "epoch": 0.4682080924855491,
+      "eval_loss": 2.2803900241851807,
+      "eval_runtime": 32.5338,
+      "eval_samples_per_second": 4.488,
+      "eval_steps_per_second": 0.584,
+      "step": 81
+    },
+    {
+      "epoch": 0.47398843930635837,
+      "grad_norm": 13.889911651611328,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.5221,
+      "step": 82
+    },
+    {
+      "epoch": 0.4797687861271676,
+      "grad_norm": 11.334454536437988,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 3.4398,
+      "step": 83
+    },
+    {
+      "epoch": 0.48554913294797686,
+      "grad_norm": 12.778782844543457,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.5363,
+      "step": 84
+    },
+    {
+      "epoch": 0.4913294797687861,
+      "grad_norm": 11.753548622131348,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.576,
+      "step": 85
+    },
+    {
+      "epoch": 0.49710982658959535,
+      "grad_norm": 11.410307884216309,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.1354,
+      "step": 86
+    },
+    {
+      "epoch": 0.5028901734104047,
+      "grad_norm": 8.957868576049805,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.5224,
+      "step": 87
+    },
+    {
+      "epoch": 0.5086705202312138,
+      "grad_norm": 15.306970596313477,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.7779,
+      "step": 88
+    },
+    {
+      "epoch": 0.5144508670520231,
+      "grad_norm": 10.743468284606934,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.8461,
+      "step": 89
+    },
+    {
+      "epoch": 0.5202312138728323,
+      "grad_norm": 9.884764671325684,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.5365,
+      "step": 90
+    },
+    {
+      "epoch": 0.5202312138728323,
+      "eval_loss": 2.251675605773926,
+      "eval_runtime": 32.5325,
+      "eval_samples_per_second": 4.488,
+      "eval_steps_per_second": 0.584,
+      "step": 90
+    },
+    {
+      "epoch": 0.5260115606936416,
+      "grad_norm": 9.051831245422363,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9364,
+      "step": 91
+    },
+    {
+      "epoch": 0.5317919075144508,
+      "grad_norm": 13.44649887084961,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.2922,
+      "step": 92
+    },
+    {
+      "epoch": 0.5375722543352601,
+      "grad_norm": 9.797504425048828,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.5593,
+      "step": 93
+    },
+    {
+      "epoch": 0.5433526011560693,
+      "grad_norm": 11.674943923950195,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.9699,
+      "step": 94
+    },
+    {
+      "epoch": 0.5491329479768786,
+      "grad_norm": 8.266894340515137,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7054,
+      "step": 95
+    },
+    {
+      "epoch": 0.5549132947976878,
+      "grad_norm": 12.257719039916992,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.0088,
+      "step": 96
+    },
+    {
+      "epoch": 0.5606936416184971,
+      "grad_norm": 12.329103469848633,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 4.0794,
+      "step": 97
+    },
+    {
+      "epoch": 0.5664739884393064,
+      "grad_norm": 13.644766807556152,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.8662,
+      "step": 98
+    },
+    {
+      "epoch": 0.5722543352601156,
+      "grad_norm": 7.874459743499756,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.4249,
+      "step": 99
+    },
+    {
+      "epoch": 0.5722543352601156,
+      "eval_loss": 2.246007204055786,
+      "eval_runtime": 32.5444,
+      "eval_samples_per_second": 4.486,
+      "eval_steps_per_second": 0.584,
+      "step": 99
+    },
+    {
+      "epoch": 0.5780346820809249,
+      "grad_norm": 10.751273155212402,
+      "learning_rate": 0.0,
+      "loss": 2.4663,
+      "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