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:d786fc7e893dd3bc3c6e08ad5f10ace078222c2cc9a685a75666ad3bf14cd8d0
+oid sha256:2c34a98cfa104e1761e26722d9e257bab07cd0696f48fe81dd1ee83747c4fcde
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2de3eb978d78cf8dcd25266d931003e51678df821e08cff04b530f5c9551034a
+oid sha256:299ad2c1abc4d06b1320a67722c4330181ef9169683b13f1ff338a1d5f4bcedc
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90ea1f3b22acd0d3c9afd160819677f0b4035afb74fff9b7ea6a0acd9c10b37a
+oid sha256:8ac108aa9eba00358310a4439f789a188dfe5197c585ee0c9b69af254e4ad32c
 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": 0.03508771929824561,
+  "epoch": 0.07017543859649122,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 26.809,
       "eval_steps_per_second": 13.405,
       "step": 5
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 4.122745990753174,
+      "learning_rate": 6e-05,
+      "loss": 20.2028,
+      "step": 6
+    },
+    {
+      "epoch": 0.04912280701754386,
+      "grad_norm": 3.8199222087860107,
+      "learning_rate": 7e-05,
+      "loss": 17.6577,
+      "step": 7
+    },
+    {
+      "epoch": 0.056140350877192984,
+      "grad_norm": 4.428239822387695,
+      "learning_rate": 8e-05,
+      "loss": 17.0906,
+      "step": 8
+    },
+    {
+      "epoch": 0.06315789473684211,
+      "grad_norm": 4.9802751541137695,
+      "learning_rate": 9e-05,
+      "loss": 16.6059,
+      "step": 9
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 5.734658241271973,
+      "learning_rate": 0.0001,
+      "loss": 16.6593,
+      "step": 10
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "eval_loss": 1.0094025135040283,
+      "eval_runtime": 9.0546,
+      "eval_samples_per_second": 26.506,
+      "eval_steps_per_second": 13.253,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5374872498733056.0,
+  "total_flos": 1.0871901190619136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null