Training in progress, step 2640, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09f4952dfa3428aca2c1575fa34747e5f6666aaf7e2613abd8099507cce9d64f
+oid sha256:0000bbde3dcfa655946e65ba64b87f6dfeccdafdb1ea253bdb538beadca3e2c8
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2dc1feaa27f4960c5b987e34d3adacdc59e0bd9286eb375d733edcb69b45b2
+oid sha256:b083f483839d99e8ac45ae2be560977e810fb410bb8320e1ced4f7ba0955e463
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5151ca7e89138bc5e58bcff1bca431f336f49a4dbf5210fb5304f6ccdc5f5fd
+oid sha256:e793c6900656f10a2db884b32b210a11518f8eaa9b09fba8fb850e868ac57958
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0393290c0ec4f4951317a3da41220b93fbef7d67af7626ecc076b5555bdbb9a9
+oid sha256:fb9e8f81be6bfdad3c91514c14230cbe82f9f3e206c903e15baf685a171dafda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9373881932021467,
+  "epoch": 0.9445438282647585,
   "eval_steps": 500,
-  "global_step": 2620,
+  "global_step": 2640,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2103,14 +2103,30 @@
       "loss": 0.4048,
       "num_input_tokens_seen": 1777203,
       "step": 2620
+    },
+    {
+      "epoch": 0.9409660107334525,
+      "grad_norm": 0.43130627274513245,
+      "learning_rate": 1.1806797853309482e-05,
+      "loss": 0.3858,
+      "num_input_tokens_seen": 1783302,
+      "step": 2630
+    },
+    {
+      "epoch": 0.9445438282647585,
+      "grad_norm": 0.3261716365814209,
+      "learning_rate": 1.1091234347048302e-05,
+      "loss": 0.3877,
+      "num_input_tokens_seen": 1790778,
+      "step": 2640
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1777203,
+  "num_input_tokens_seen": 1790778,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.996301946954342e+16,
+  "total_flos": 4.026827328089702e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null