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:baaaa5f8fc5fb86c2a0355f35ded415535e9465522bcde9b32b470ad787b9fb4
+oid sha256:3613eb1b993ffed95cd9f1d3369deaafea3fc2c443fde192406856824013e03d
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a13bade6aa84cd22229c27985a95607536c889bb393661c28a8e128fb88ff3
+oid sha256:8392a8145b095f8f0e1b8e6e84141acd17c5a7c16241ea55b2136c4199a8ae28
 size 25784826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719020131bf833c90632c6b01b06c5301e1876ba50a1273eb06ec350ba411a1a
+oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
 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": 0.007263203841117416,
+  "epoch": 0.010894805761676124,
   "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": 6.783,
       "eval_steps_per_second": 3.392,
       "step": 26
+    },
+    {
+      "epoch": 0.0075425578350065475,
+      "grad_norm": 7.612943649291992,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 19.8984,
+      "step": 27
+    },
+    {
+      "epoch": 0.007821911828895679,
+      "grad_norm": 7.850345134735107,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 18.8711,
+      "step": 28
+    },
+    {
+      "epoch": 0.00810126582278481,
+      "grad_norm": 8.194131851196289,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 18.4531,
+      "step": 29
+    },
+    {
+      "epoch": 0.008380619816673941,
+      "grad_norm": 8.798739433288574,
+      "learning_rate": 5e-05,
+      "loss": 20.082,
+      "step": 30
+    },
+    {
+      "epoch": 0.008659973810563073,
+      "grad_norm": 4.806086540222168,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 18.3242,
+      "step": 31
+    },
+    {
+      "epoch": 0.008939327804452205,
+      "grad_norm": 6.420837879180908,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 17.5234,
+      "step": 32
+    },
+    {
+      "epoch": 0.009218681798341335,
+      "grad_norm": 5.769430637359619,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 19.3711,
+      "step": 33
+    },
+    {
+      "epoch": 0.009498035792230467,
+      "grad_norm": 6.312093734741211,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 17.0234,
+      "step": 34
+    },
+    {
+      "epoch": 0.0097773897861196,
+      "grad_norm": 10.681304931640625,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 19.4766,
+      "step": 35
+    },
+    {
+      "epoch": 0.01005674378000873,
+      "grad_norm": 8.919983863830566,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 16.9336,
+      "step": 36
+    },
+    {
+      "epoch": 0.010336097773897861,
+      "grad_norm": 7.540457725524902,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 17.8359,
+      "step": 37
+    },
+    {
+      "epoch": 0.010615451767786993,
+      "grad_norm": 6.8388752937316895,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 19.4062,
+      "step": 38
+    },
+    {
+      "epoch": 0.010894805761676124,
+      "grad_norm": 5.113622188568115,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 17.5781,
+      "step": 39
+    },
+    {
+      "epoch": 0.010894805761676124,
+      "eval_loss": 1.1385672092437744,
+      "eval_runtime": 888.7356,
+      "eval_samples_per_second": 6.784,
+      "eval_steps_per_second": 3.392,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.647045675627315e+16,
+  "total_flos": 3.961564956721152e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null