Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81f4aaad24fff81216f61fa97454071908d8fe7bb8736c35c8f517d83bf33559
+oid sha256:e9dcc53a316311354c1bf860f9366995ee7faa8e6181d3b3866aa3dabba8cd18
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1969f4226cf8fa608037e0d127eef9171d2348e73cf24cc6e6f91d1f6f89bc5
+oid sha256:23e7b7b0af1a17294fe4689170796c76185c4d82cbae0066f2b506ab8770d3b8
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db27c6c95f1f5eabafb82c2066a5554f04ee4d86f42abe3f306967bd94dc602a
+oid sha256:4b976fe13df9d590838338fd3331460eb1554057da1cd4564745a089b6e6b692
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00042201283892906124,
+  "epoch": 0.0006330192583935919,
   "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": 16.64,
       "eval_steps_per_second": 8.321,
       "step": 26
+    },
+    {
+      "epoch": 0.00043824410196479437,
+      "grad_norm": 4.566595554351807,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 2.0687,
+      "step": 27
+    },
+    {
+      "epoch": 0.0004544753650005275,
+      "grad_norm": 3.230044364929199,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 1.7262,
+      "step": 28
+    },
+    {
+      "epoch": 0.0004707066280362606,
+      "grad_norm": 3.278032064437866,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 1.9874,
+      "step": 29
+    },
+    {
+      "epoch": 0.00048693789107199376,
+      "grad_norm": 3.22609281539917,
+      "learning_rate": 2.5e-05,
+      "loss": 1.4016,
+      "step": 30
+    },
+    {
+      "epoch": 0.0005031691541077269,
+      "grad_norm": 4.10092830657959,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 1.6499,
+      "step": 31
+    },
+    {
+      "epoch": 0.00051940041714346,
+      "grad_norm": 3.619818925857544,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 1.836,
+      "step": 32
+    },
+    {
+      "epoch": 0.0005356316801791932,
+      "grad_norm": 3.6569910049438477,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 1.8563,
+      "step": 33
+    },
+    {
+      "epoch": 0.0005518629432149263,
+      "grad_norm": 3.3132452964782715,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 1.527,
+      "step": 34
+    },
+    {
+      "epoch": 0.0005680942062506593,
+      "grad_norm": 3.2675442695617676,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 1.7821,
+      "step": 35
+    },
+    {
+      "epoch": 0.0005843254692863925,
+      "grad_norm": 3.574618339538574,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 1.6777,
+      "step": 36
+    },
+    {
+      "epoch": 0.0006005567323221256,
+      "grad_norm": 3.5887537002563477,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 1.9313,
+      "step": 37
+    },
+    {
+      "epoch": 0.0006167879953578588,
+      "grad_norm": 4.172155857086182,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 1.5391,
+      "step": 38
+    },
+    {
+      "epoch": 0.0006330192583935919,
+      "grad_norm": 3.490973711013794,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 1.653,
+      "step": 39
+    },
+    {
+      "epoch": 0.0006330192583935919,
+      "eval_loss": 0.42761555314064026,
+      "eval_runtime": 1558.3122,
+      "eval_samples_per_second": 16.647,
+      "eval_steps_per_second": 8.324,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7887014036766720.0,
+  "total_flos": 1.1874337799798784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null