Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d2b88714eb6cb306741941bfc68abe335fd33fbfb2475c98c413a3a11163490
+oid sha256:43ae9755626e2950d8c06fdf1d60414796248dfc072fc65db072fe182e1cf597
 size 1912664024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed0fd52e80191d03c1e20ea9651314992b50ddfd7ee286e16b6cf46053fb5109
+oid sha256:7f97b6951acc478b8072c3a2f936c84025fc1e144d1addcc1796e7e406ff11a9
 size 958697812

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c3cdbf034ef9f86029f99db82daec670863e67518e294d6fbac9a3fc658d9d
+oid sha256:4d9b92fa45e44153a07435b55d5d3d71bf302bfd9a3b3f027d29977fda525192
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f792c7a8589566dc7799352d28793eedc78c2ddc18916075011990a0efec9786
+oid sha256:520ffe1792334414c9404c774e2e9174a1306a63c3f66ae705923c2d8b0a934b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.030676728633658508,
+  "epoch": 0.03374440149702436,
   "eval_steps": 20,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -382,6 +382,36 @@
       "eval_samples_per_second": 4.247,
       "eval_steps_per_second": 0.552,
       "step": 500
+    },
+    {
+      "epoch": 0.031903797779004844,
+      "grad_norm": 0.16019868850708008,
+      "learning_rate": 0.00019367865471952867,
+      "loss": 1.4778,
+      "step": 520
+    },
+    {
+      "epoch": 0.031903797779004844,
+      "eval_loss": 1.4597880840301514,
+      "eval_runtime": 23.624,
+      "eval_samples_per_second": 4.233,
+      "eval_steps_per_second": 0.55,
+      "step": 520
+    },
+    {
+      "epoch": 0.03313086692435119,
+      "grad_norm": 0.1370091289281845,
+      "learning_rate": 0.00019343316558242298,
+      "loss": 1.5531,
+      "step": 540
+    },
+    {
+      "epoch": 0.03313086692435119,
+      "eval_loss": 1.443243384361267,
+      "eval_runtime": 23.5537,
+      "eval_samples_per_second": 4.246,
+      "eval_steps_per_second": 0.552,
+      "step": 540
     }
   ],
   "logging_steps": 20,
@@ -389,7 +419,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 50,
-  "total_flos": 3.63154250124288e+16,
+  "total_flos": 3.97156971856896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null