Training in progress, step 210, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2a60feb1e96d790294c0b5eae9acc5fb705f4771269491fe8bf9cd16a835e5
+oid sha256:2bc6d404f7fd69fe907c7d54d9d2ba1b802a5e0867a87634f546ea28477a5f17
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cbcfaf89e28391d7c82167b07cd38f9662d61b8bf262f3ab44b55dd4fde9bc5
+oid sha256:32ee2b6ae3076a559fcb80a8ff9862fd211c95d781fac1e407e8f1030ac38660
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98eb662dc5bc7d04a24c041329941502e3aed4d1fcb64bac57ca17d20f66e522
+oid sha256:2a58fcd0d4e63bda996273295cf19629f45f15b4f31eb5cecaee6502ebb86992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f516a6e4e8a8eba956b80cb2ea416b9fd98f0dec12d7d9d9a36274d0eef4a63
+oid sha256:4bd95a1db0e917ddf11b12a343f06e907fcec4b81104002e2471b4778587b465
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03521643433602348,
+  "epoch": 0.04402054292002935,
   "eval_steps": 42,
-  "global_step": 168,
+  "global_step": 210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -439,6 +439,112 @@
       "eval_samples_per_second": 48.695,
       "eval_steps_per_second": 6.091,
       "step": 168
+    },
+    {
+      "epoch": 0.03584529923488104,
+      "grad_norm": 0.3241373300552368,
+      "learning_rate": 7.564496387029532e-05,
+      "loss": 1.1243,
+      "step": 171
+    },
+    {
+      "epoch": 0.0364741641337386,
+      "grad_norm": 0.33574438095092773,
+      "learning_rate": 7.481469062821252e-05,
+      "loss": 1.1031,
+      "step": 174
+    },
+    {
+      "epoch": 0.037103029032596165,
+      "grad_norm": 0.38013267517089844,
+      "learning_rate": 7.39752373250527e-05,
+      "loss": 1.1191,
+      "step": 177
+    },
+    {
+      "epoch": 0.03773189393145373,
+      "grad_norm": 0.35769525170326233,
+      "learning_rate": 7.312691451204178e-05,
+      "loss": 1.0992,
+      "step": 180
+    },
+    {
+      "epoch": 0.03836075883031129,
+      "grad_norm": 0.32820338010787964,
+      "learning_rate": 7.227003602163295e-05,
+      "loss": 1.0621,
+      "step": 183
+    },
+    {
+      "epoch": 0.03898962372916885,
+      "grad_norm": 0.32962238788604736,
+      "learning_rate": 7.14049188514063e-05,
+      "loss": 1.0828,
+      "step": 186
+    },
+    {
+      "epoch": 0.03961848862802641,
+      "grad_norm": 0.34197545051574707,
+      "learning_rate": 7.05318830467969e-05,
+      "loss": 1.1168,
+      "step": 189
+    },
+    {
+      "epoch": 0.040247353526883974,
+      "grad_norm": 0.37021368741989136,
+      "learning_rate": 6.965125158269619e-05,
+      "loss": 1.1374,
+      "step": 192
+    },
+    {
+      "epoch": 0.04087621842574154,
+      "grad_norm": 0.3301369547843933,
+      "learning_rate": 6.876335024396872e-05,
+      "loss": 1.054,
+      "step": 195
+    },
+    {
+      "epoch": 0.041505083324599096,
+      "grad_norm": 0.35479190945625305,
+      "learning_rate": 6.786850750493006e-05,
+      "loss": 1.0923,
+      "step": 198
+    },
+    {
+      "epoch": 0.04213394822345666,
+      "grad_norm": 0.35211730003356934,
+      "learning_rate": 6.696705440782938e-05,
+      "loss": 1.1124,
+      "step": 201
+    },
+    {
+      "epoch": 0.042762813122314225,
+      "grad_norm": 0.4026525616645813,
+      "learning_rate": 6.605932444038229e-05,
+      "loss": 1.1229,
+      "step": 204
+    },
+    {
+      "epoch": 0.04339167802117178,
+      "grad_norm": 0.40407177805900574,
+      "learning_rate": 6.514565341239861e-05,
+      "loss": 1.066,
+      "step": 207
+    },
+    {
+      "epoch": 0.04402054292002935,
+      "grad_norm": 0.3534255027770996,
+      "learning_rate": 6.422637933155162e-05,
+      "loss": 1.0462,
+      "step": 210
+    },
+    {
+      "epoch": 0.04402054292002935,
+      "eval_loss": 1.0946003198623657,
+      "eval_runtime": 165.0602,
+      "eval_samples_per_second": 48.679,
+      "eval_steps_per_second": 6.089,
+      "step": 210
     }
   ],
   "logging_steps": 3,
@@ -458,7 +564,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.5836883921534976e+16,
+  "total_flos": 4.479610490191872e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null