Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fe3155abb44418ad3ec5aab27c9a471f9149f7e00d67b2bda22953d7553f200
+oid sha256:7d2b88714eb6cb306741941bfc68abe335fd33fbfb2475c98c413a3a11163490
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7b8617fe9900b0db6ad49b6444c1394a7b5269449f30267908e3da6ced93a3
+oid sha256:ed0fd52e80191d03c1e20ea9651314992b50ddfd7ee286e16b6cf46053fb5109
 size 958697812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6844cd586de68a6e1a4752382bd60051acd338bfb31d133b33aba14fbb697dfc
+oid sha256:c6c3cdbf034ef9f86029f99db82daec670863e67518e294d6fbac9a3fc658d9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb632d0e7d322b6e88da441db58b5c2d007cbabbb9a0c6e908d28d2b74fb4de2
+oid sha256:f792c7a8589566dc7799352d28793eedc78c2ddc18916075011990a0efec9786
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.027609055770292656,
+  "epoch": 0.030676728633658508,
   "eval_steps": 20,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -337,6 +337,51 @@
       "eval_samples_per_second": 4.221,
       "eval_steps_per_second": 0.549,
       "step": 440
+    },
+    {
+      "epoch": 0.028222590342965825,
+      "grad_norm": 0.14759239554405212,
+      "learning_rate": 0.00019441512213084572,
+      "loss": 1.5735,
+      "step": 460
+    },
+    {
+      "epoch": 0.028222590342965825,
+      "eval_loss": 1.486402988433838,
+      "eval_runtime": 23.2911,
+      "eval_samples_per_second": 4.293,
+      "eval_steps_per_second": 0.558,
+      "step": 460
+    },
+    {
+      "epoch": 0.029449659488312168,
+      "grad_norm": 0.11428073793649673,
+      "learning_rate": 0.00019416963299374006,
+      "loss": 1.5788,
+      "step": 480
+    },
+    {
+      "epoch": 0.029449659488312168,
+      "eval_loss": 1.4712104797363281,
+      "eval_runtime": 23.4851,
+      "eval_samples_per_second": 4.258,
+      "eval_steps_per_second": 0.554,
+      "step": 480
+    },
+    {
+      "epoch": 0.030676728633658508,
+      "grad_norm": 0.11649870127439499,
+      "learning_rate": 0.00019392414385663436,
+      "loss": 1.5667,
+      "step": 500
+    },
+    {
+      "epoch": 0.030676728633658508,
+      "eval_loss": 1.4620152711868286,
+      "eval_runtime": 23.5455,
+      "eval_samples_per_second": 4.247,
+      "eval_steps_per_second": 0.552,
+      "step": 500
     }
   ],
   "logging_steps": 20,
@@ -344,7 +389,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 50,
-  "total_flos": 3.28358598672384e+16,
+  "total_flos": 3.63154250124288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null