Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1988a1db74d5c9129b157c19b51ea7207ba60c2aebaed3965a9450c632ddd421
+oid sha256:248cbbd82e9755de0339732f8187bd25681cb18587f34c3a91de0c96b75a0903
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b252f5b095fd0053ada5a06757aef7478edd59ef0bd5dfa621de7ede148772e7
+oid sha256:bdf99b95fd8f09b146edc1a601ec72c07d7e8d6d93d27f491cd2e1b40fbef6b3
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad92fd4b5f7e6a6a5f26004088019a02ea35ba88f09d7fe4ea750d8038814f9
+oid sha256:50b8919ca363c2d41227a64b0d311c6bf7efdeaeae1142284b6297cc2caca67d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3673469387755102,
+  "epoch": 0.413265306122449,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 592.608,
       "eval_steps_per_second": 150.846,
       "step": 72
+    },
+    {
+      "epoch": 0.3826530612244898,
+      "grad_norm": 0.20278629660606384,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 6.8285,
+      "step": 75
+    },
+    {
+      "epoch": 0.3979591836734694,
+      "grad_norm": 0.19427503645420074,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 6.8339,
+      "step": 78
+    },
+    {
+      "epoch": 0.413265306122449,
+      "grad_norm": 0.2242947667837143,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 6.8312,
+      "step": 81
+    },
+    {
+      "epoch": 0.413265306122449,
+      "eval_loss": 6.827848434448242,
+      "eval_runtime": 0.2684,
+      "eval_samples_per_second": 614.721,
+      "eval_steps_per_second": 156.474,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 692012187648.0,
+  "total_flos": 778513711104.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null