Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d640bb3327b6a9bf2a1c9dc18d6446a17c2ffd6627b7b77a68aa3ffe2a9f25c
+oid sha256:c98af77b8a3675a3a3d59cff821020365655bb996ac27b7508e06c0dcec07dd0
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b4eb718f0abd9d2109686e32a14935ad5a611b08dbb2dd292d9ca2f7c9ef3e
+oid sha256:6317ec58bdeadc44e557f74bf998e742cdd060b2154e0b6550b9778ed7a9b10d
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd00f6ef24893c2cb2c5f5fe0977bea81671980f15f5b3943ce9acb62cdfb54
+oid sha256:cab217bfbd941235d8f4ba65bc226fe1d7488d7dc3ee7690705b5eec7f2766d7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01898272085665612,
+  "epoch": 0.02433682161109759,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.5809,
       "step": 35
+    },
+    {
+      "epoch": 0.019469457288878073,
+      "grad_norm": 0.23061084747314453,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5599,
+      "step": 40
+    },
+    {
+      "epoch": 0.019469457288878073,
+      "eval_loss": 0.6510303020477295,
+      "eval_runtime": 34.4529,
+      "eval_samples_per_second": 25.107,
+      "eval_steps_per_second": 12.568,
+      "step": 40
+    },
+    {
+      "epoch": 0.02190313944998783,
+      "grad_norm": 0.26074719429016113,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.663,
+      "step": 45
+    },
+    {
+      "epoch": 0.02433682161109759,
+      "grad_norm": 0.28464382886886597,
+      "learning_rate": 0.0,
+      "loss": 0.5881,
+      "step": 50
+    },
+    {
+      "epoch": 0.02433682161109759,
+      "eval_loss": 0.6507804989814758,
+      "eval_runtime": 34.2813,
+      "eval_samples_per_second": 25.232,
+      "eval_steps_per_second": 12.631,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1645813661958144.0,
+  "total_flos": 2124153593266176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null