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:a3feb46c97d7d92c3b3e5ee18d7535b99d1eaa76e55d7e1db50b631f9e7f0758
+oid sha256:640fb97455fc6057d1c7fc2b42a196c78995e9168f3a2a810db6839300c2762c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b16d45d1a0af4a7cb93e7962406421a692d6fa6a1c621d2f3c2422c5be21cf08
+oid sha256:baef85c1828d77eb506f5d52be066bcd1bd47c0105f1e78b89038a6652bda682
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c103f85206916bbddbfdec4d0ebb18b19e3d0dd8d88c9b4c12898c57e206a7e
+oid sha256:0c72461d8b102f8348796119289aad1a7993b551f980fac40ec203302a5c72e0
 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": 0.0017722489668981383,
+  "epoch": 0.0026583734503472073,
   "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": 6.824,
       "eval_steps_per_second": 3.412,
       "step": 26
+    },
+    {
+      "epoch": 0.001840412388701913,
+      "grad_norm": 3.756096839904785,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 0.6924,
+      "step": 27
+    },
+    {
+      "epoch": 0.0019085758105056873,
+      "grad_norm": 2.65657901763916,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 0.4216,
+      "step": 28
+    },
+    {
+      "epoch": 0.001976739232309462,
+      "grad_norm": 3.051575183868408,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 0.6558,
+      "step": 29
+    },
+    {
+      "epoch": 0.0020449026541132366,
+      "grad_norm": 3.750715494155884,
+      "learning_rate": 5e-05,
+      "loss": 0.5206,
+      "step": 30
+    },
+    {
+      "epoch": 0.002113066075917011,
+      "grad_norm": 2.827176094055176,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 0.531,
+      "step": 31
+    },
+    {
+      "epoch": 0.0021812294977207854,
+      "grad_norm": 3.170285940170288,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.7352,
+      "step": 32
+    },
+    {
+      "epoch": 0.00224939291952456,
+      "grad_norm": 4.301424026489258,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.9347,
+      "step": 33
+    },
+    {
+      "epoch": 0.0023175563413283347,
+      "grad_norm": 3.8904523849487305,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.58,
+      "step": 34
+    },
+    {
+      "epoch": 0.0023857197631321093,
+      "grad_norm": 3.3350067138671875,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.652,
+      "step": 35
+    },
+    {
+      "epoch": 0.002453883184935884,
+      "grad_norm": 3.35461163520813,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.8035,
+      "step": 36
+    },
+    {
+      "epoch": 0.0025220466067396585,
+      "grad_norm": 3.971146583557129,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.6434,
+      "step": 37
+    },
+    {
+      "epoch": 0.0025902100285434327,
+      "grad_norm": 2.744048833847046,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.468,
+      "step": 38
+    },
+    {
+      "epoch": 0.0026583734503472073,
+      "grad_norm": 3.2330892086029053,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.5389,
+      "step": 39
+    },
+    {
+      "epoch": 0.0026583734503472073,
+      "eval_loss": 0.612258791923523,
+      "eval_runtime": 3622.0619,
+      "eval_samples_per_second": 6.822,
+      "eval_steps_per_second": 3.411,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.543125549805732e+17,
+  "total_flos": 2.3146883247085978e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null