Training in progress, step 252, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971e54de63920eed6700963a65c28021c96f5ce4caf96cc351d0df00fb6d803c
+oid sha256:dd129a1bd9e3d8ee5a1e5db9d958aed101562fb77fbab566965c550cf4cf930d
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54c1dc870cb0fc047cba8029354bda92e92efcf53a26b597de339883b64b86e3
+oid sha256:f8c1d468e59b49e68a6e930bd1f26d86439dccd611e450f66da506396b180023
 size 51613348

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d8588f6659622a3919c79527db3d98a5bae8354f3a9892e08b902b222082b
+oid sha256:f261dee394c5079254fc75fbcc32a19145fa5f61c502d9043aac58db31a15775
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d485fc873443ef7ad597c6f4a82e93694f8fe8522b8ffecf4d60075246020043
+oid sha256:fde5cce913d9c5501edc422466fae8378d9b13dc57f22397ec7fc38f7801fc24
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03145949589903,
+  "epoch": 0.037751395078836,
   "eval_steps": 42,
-  "global_step": 210,
+  "global_step": 252,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -545,6 +545,112 @@
       "eval_samples_per_second": 35.956,
       "eval_steps_per_second": 4.497,
       "step": 210
+    },
+    {
+      "epoch": 0.031908917269016145,
+      "grad_norm": 0.15568239986896515,
+      "learning_rate": 3.165092113916688e-05,
+      "loss": 1.12,
+      "step": 213
+    },
+    {
+      "epoch": 0.03235833863900228,
+      "grad_norm": 0.16250278055667877,
+      "learning_rate": 3.118619214012286e-05,
+      "loss": 1.0651,
+      "step": 216
+    },
+    {
+      "epoch": 0.032807760008988426,
+      "grad_norm": 0.16043943166732788,
+      "learning_rate": 3.071917459263264e-05,
+      "loss": 1.1254,
+      "step": 219
+    },
+    {
+      "epoch": 0.03325718137897457,
+      "grad_norm": 0.19213679432868958,
+      "learning_rate": 3.0250041267321232e-05,
+      "loss": 1.1082,
+      "step": 222
+    },
+    {
+      "epoch": 0.033706602748960715,
+      "grad_norm": 0.17149952054023743,
+      "learning_rate": 2.9778965717534313e-05,
+      "loss": 1.0345,
+      "step": 225
+    },
+    {
+      "epoch": 0.03415602411894685,
+      "grad_norm": 0.19161058962345123,
+      "learning_rate": 2.9306122215132976e-05,
+      "loss": 1.2631,
+      "step": 228
+    },
+    {
+      "epoch": 0.034605445488933,
+      "grad_norm": 0.12983594834804535,
+      "learning_rate": 2.8831685686022897e-05,
+      "loss": 1.0125,
+      "step": 231
+    },
+    {
+      "epoch": 0.03505486685891914,
+      "grad_norm": 0.1923818439245224,
+      "learning_rate": 2.8355831645441388e-05,
+      "loss": 1.1152,
+      "step": 234
+    },
+    {
+      "epoch": 0.035504288228905286,
+      "grad_norm": 0.17539535462856293,
+      "learning_rate": 2.787873613302649e-05,
+      "loss": 1.0698,
+      "step": 237
+    },
+    {
+      "epoch": 0.03595370959889143,
+      "grad_norm": 0.20096057653427124,
+      "learning_rate": 2.7400575647692046e-05,
+      "loss": 1.0742,
+      "step": 240
+    },
+    {
+      "epoch": 0.03640313096887757,
+      "grad_norm": 0.1583949774503708,
+      "learning_rate": 2.692152708233292e-05,
+      "loss": 1.0255,
+      "step": 243
+    },
+    {
+      "epoch": 0.03685255233886371,
+      "grad_norm": 0.13673090934753418,
+      "learning_rate": 2.6441767658384366e-05,
+      "loss": 1.1167,
+      "step": 246
+    },
+    {
+      "epoch": 0.037301973708849856,
+      "grad_norm": 0.15132947266101837,
+      "learning_rate": 2.596147486025996e-05,
+      "loss": 1.053,
+      "step": 249
+    },
+    {
+      "epoch": 0.037751395078836,
+      "grad_norm": 0.1649513989686966,
+      "learning_rate": 2.5480826369692178e-05,
+      "loss": 1.1041,
+      "step": 252
+    },
+    {
+      "epoch": 0.037751395078836,
+      "eval_loss": 1.0942788124084473,
+      "eval_runtime": 312.947,
+      "eval_samples_per_second": 35.926,
+      "eval_steps_per_second": 4.493,
+      "step": 252
     }
   ],
   "logging_steps": 3,
@@ -564,7 +670,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.724628513606861e+16,
+  "total_flos": 8.058094740937114e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null