Training in progress, step 200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd92eac0c175facf66bcc6744b550abe565351d58bfc65728501b0eb34deb6a
+oid sha256:d54587f0b1a198dd39c4ae5e433126d643f66f0ed0846d561ef67c3037c9a48e
 size 250490408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5a2c0147463a169de4f6d49d24c6bab30ce74a9cdea031b1cbd9a46e14a1a3
+oid sha256:1b18511a4e4cf4754059d13bb09b4648a957c0877ea68b53a97a0ab51ece6344
 size 255265850

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb8f173dc69af6518470d76de345e8f28d66983c49c7120eb4118b25379494c
+oid sha256:d99c128ab1f240cd1c4228cbdcc4238c34c69acef749723e334ae111d48356bc
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef1dfb8026c7c70f38bd139303377768a0568a232a11e705dcdc6c898cedb8c3
+oid sha256:19e465ffabd9644ccbc2caf12ae583025fdb275dc63c3b925248b2abc2e151ad
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9f0e9fcb3fec99611921d8f34980406ad06f308daea00535e4da9839a46d96
+oid sha256:9cd11d413bc67bf01de9a1a006e9e7655be307353028b25f5b3c299e5b6b7a44
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.0,
+  "epoch": 16.666666666666668,
   "eval_steps": 40,
-  "global_step": 180,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -173,6 +173,28 @@
       "learning_rate": 0.00016772815716257412,
       "loss": 3.4769,
       "step": 180
+    },
+    {
+      "epoch": 15.833333333333334,
+      "grad_norm": 5.6875,
+      "learning_rate": 0.00016357237482099684,
+      "loss": 3.3954,
+      "step": 190
+    },
+    {
+      "epoch": 16.666666666666668,
+      "grad_norm": 3.921875,
+      "learning_rate": 0.00015922352526649803,
+      "loss": 3.3223,
+      "step": 200
+    },
+    {
+      "epoch": 16.666666666666668,
+      "eval_loss": 3.2679085731506348,
+      "eval_runtime": 10.4994,
+      "eval_samples_per_second": 142.96,
+      "eval_steps_per_second": 2.286,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -192,7 +214,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1658850390245376e+16,
+  "total_flos": 1.2971581575790592e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null