Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd8999f4f20f203a48ab2768a173ae6e22f7ef059d5922acbdb6f7f93cdaa31a
+oid sha256:74c61a13d663d773c74fa8b36c72e1431ebf9cd271e9282391111e52151d52b2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56430a939b2e00864acd65d2c40a4a33d9dfe8c64027c6eab18d450528032a2
+oid sha256:fd18025b932ac0357eb201ad8d9476a484fa40d354ee1b644139b59b883e1485
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
+oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06202475026092143,
+  "epoch": 0.09303712539138213,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 42.447,
       "eval_steps_per_second": 21.223,
       "step": 26
+    },
+    {
+      "epoch": 0.06441031757864918,
+      "grad_norm": 0.386901319026947,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.1078,
+      "step": 27
+    },
+    {
+      "epoch": 0.06679588489637692,
+      "grad_norm": 0.4116002321243286,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.1013,
+      "step": 28
+    },
+    {
+      "epoch": 0.06918145221410467,
+      "grad_norm": 0.34669479727745056,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.1137,
+      "step": 29
+    },
+    {
+      "epoch": 0.07156701953183241,
+      "grad_norm": 0.3983478844165802,
+      "learning_rate": 5e-05,
+      "loss": 0.0615,
+      "step": 30
+    },
+    {
+      "epoch": 0.07395258684956016,
+      "grad_norm": 0.3107887804508209,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.0543,
+      "step": 31
+    },
+    {
+      "epoch": 0.07633815416728791,
+      "grad_norm": 0.3019241690635681,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0502,
+      "step": 32
+    },
+    {
+      "epoch": 0.07872372148501565,
+      "grad_norm": 0.33337318897247314,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0531,
+      "step": 33
+    },
+    {
+      "epoch": 0.0811092888027434,
+      "grad_norm": 0.29022204875946045,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0534,
+      "step": 34
+    },
+    {
+      "epoch": 0.08349485612047115,
+      "grad_norm": 0.28613466024398804,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0643,
+      "step": 35
+    },
+    {
+      "epoch": 0.08588042343819889,
+      "grad_norm": 0.29469338059425354,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0625,
+      "step": 36
+    },
+    {
+      "epoch": 0.08826599075592664,
+      "grad_norm": 0.31243982911109924,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.053,
+      "step": 37
+    },
+    {
+      "epoch": 0.0906515580736544,
+      "grad_norm": 0.2379445880651474,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0362,
+      "step": 38
+    },
+    {
+      "epoch": 0.09303712539138213,
+      "grad_norm": 0.21602892875671387,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0602,
+      "step": 39
+    },
+    {
+      "epoch": 0.09303712539138213,
+      "eval_loss": 0.05400439724326134,
+      "eval_runtime": 16.603,
+      "eval_samples_per_second": 42.522,
+      "eval_steps_per_second": 21.261,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.713735840301056e+16,
+  "total_flos": 2.570603760451584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null