Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72163366a3f7b7e8c790ff526971d282b0fc04bc4ae0bc2f2c1f8d73ba9c8633
+oid sha256:21648d5ba001cce08b16b3764c96ccf6b4fdb0ca6f2bcb1566b2d694397b9c15
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea646f2357bc66ad8a1c0d53798bd3bc8eb2a2c294ddb067f73a38510872dac
+oid sha256:8f009ab4f5ff3f5ccab8f33bd7776337b6a9d126d029d3490cada42c290ddac1
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434672bc320e504dce8f6e74bfb7b702b872a8235385e50588f42567e4f518d8
+oid sha256:786c2a878181864eaae3009c839540dd50237b1930f80d9955fbabc0ccf3cc14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027597626604112047,
+  "epoch": 0.005519525320822409,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 12.785,
       "eval_steps_per_second": 1.6,
       "step": 5
+    },
+    {
+      "epoch": 0.0033117151924934455,
+      "grad_norm": 10.630936622619629,
+      "learning_rate": 6e-05,
+      "loss": 12.5022,
+      "step": 6
+    },
+    {
+      "epoch": 0.004967572788740169,
+      "grad_norm": 13.811830520629883,
+      "learning_rate": 9e-05,
+      "loss": 8.3067,
+      "step": 9
+    },
+    {
+      "epoch": 0.005519525320822409,
+      "eval_loss": 4.47538423538208,
+      "eval_runtime": 238.5953,
+      "eval_samples_per_second": 12.792,
+      "eval_steps_per_second": 1.601,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7542567893729280.0,
+  "total_flos": 1.508513578745856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null