Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae15614e5aba83d21bbfa8fd38c5bfa8f82e6385149b49451b2e6b37df2b6d62
+oid sha256:6d9a432cd94896e81dd9f66a141f32b0b0fd201a930c75e73f510e6ddd6a6342
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffb74839748e0a213b19efdf15c1a9fdb8c1c4f020d249bcc578ad698dadf6a0
+oid sha256:d393d47f9cacdd7c7fad05ab5b0b674c811faf5e99142dc1c86af9a829210acc
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28516c7cadb08fe46441ba4a0a3ee074b2b8d9dcad2789e835ca8f0d31014ca9
+oid sha256:856de0f274a5852e320b8ff95ead26f86acb6a4a730880519f52b297245eb612
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010767884783632815,
+  "epoch": 0.01345985597954102,
   "eval_steps": 3,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,57 @@
       "learning_rate": 5.000000000000002e-05,
       "loss": 3.9268,
       "step": 20
+    },
+    {
+      "epoch": 0.011306279022814456,
+      "grad_norm": 2.2296042442321777,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.8072,
+      "step": 21
+    },
+    {
+      "epoch": 0.011306279022814456,
+      "eval_loss": 4.0160722732543945,
+      "eval_runtime": 185.5603,
+      "eval_samples_per_second": 8.434,
+      "eval_steps_per_second": 4.22,
+      "step": 21
+    },
+    {
+      "epoch": 0.011844673261996097,
+      "grad_norm": 1.9645236730575562,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 4.1506,
+      "step": 22
+    },
+    {
+      "epoch": 0.012383067501177738,
+      "grad_norm": 2.151200294494629,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.0872,
+      "step": 23
+    },
+    {
+      "epoch": 0.012921461740359378,
+      "grad_norm": 1.6876325607299805,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 4.0389,
+      "step": 24
+    },
+    {
+      "epoch": 0.012921461740359378,
+      "eval_loss": 3.9968693256378174,
+      "eval_runtime": 185.331,
+      "eval_samples_per_second": 8.444,
+      "eval_steps_per_second": 4.225,
+      "step": 24
+    },
+    {
+      "epoch": 0.01345985597954102,
+      "grad_norm": 1.7987089157104492,
+      "learning_rate": 0.0,
+      "loss": 3.944,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -217,12 +268,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.067577446170624e+16,
+  "total_flos": 3.83447180771328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null