Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4c28eed7347f49ce3c2f49f2f5d02c32769707d9bac09e91540f9ce0bcdb7d
+oid sha256:cf811b2d78872d10339cdd7b8545a8873224264a27d05be8d115aff8d26027d1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e30ea22c4fcf2cd59b920c61af983a6e3d0438f11af31107d6ce24cf8c03e76
+oid sha256:1dfc63c398fe185d106fac3af3c7653ad949e2fae5fe333809bd77918e804ee3
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858ffaf5420905109f055dc370b50c9f0db5d0f1b10c2f4496d7349612d81ec4
+oid sha256:1196200b87564fcc440e04dafa8818810b70e6b70bd8a68d5aa32697baecab70
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ea7fdc27d3a55e20051ff7c0b0952cd04b9d78f6edb951d9b6865b402accbc
+oid sha256:95dc17148d20a80420d084efd57531552658b423d2de44a1f82d74311ef7502d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.12287528158918698,
+  "epoch": 0.13652809065465218,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,28 @@
       "eval_samples_per_second": 35.232,
       "eval_steps_per_second": 8.808,
       "step": 900
+    },
+    {
+      "epoch": 0.1297016861219196,
+      "grad_norm": 110.23700714111328,
+      "learning_rate": 0.00025,
+      "loss": 9.1768,
+      "step": 950
+    },
+    {
+      "epoch": 0.13652809065465218,
+      "grad_norm": 100.71356964111328,
+      "learning_rate": 0.00025,
+      "loss": 9.0456,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13652809065465218,
+      "eval_loss": 2.4080352783203125,
+      "eval_runtime": 174.9154,
+      "eval_samples_per_second": 35.263,
+      "eval_steps_per_second": 8.816,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -227,12 +249,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.182637002784768e+17,
+  "total_flos": 3.53626333642752e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null