Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5562090f9fa1129f5aaa580645497e48d5abe9584fdafc530eeaf40813d77f16
+oid sha256:e00286fe04914af602f8620e4a50073843f2087a23b39f7a999a6314deac97ed
 size 2609498088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a1617dec427bfbc3ea454bf8d167fbc45ab9a7cba154e6897ed91525ad35dc
+oid sha256:9e4c822c18a79168516c9ff03658697c71eef8179abb9efd40071977d42c2a60
 size 5208796146

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839b1bf83e268fa72451a6eb1844dabdf138c04e5c6a0d00f0f415b37ecf6799
+oid sha256:79467bc01205da61e009aa2fbf32ec57e19156a9ee560a9b1cdbafaf10bb888e
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98b9a9b66ad7c2c92d26ff031cce36ce8f9c2ebdb6be883784d837b0e0137568
+oid sha256:17d282d44e6a12e9ca82ec6b42e7f212659678f5fe8c9a58e24a30599040d3e5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 50,
-  "global_step": 1032,
+  "global_step": 1161,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,51 @@
       "eval_samples_per_second": 37.461,
       "eval_steps_per_second": 18.731,
       "step": 1000
+    },
+    {
+      "epoch": 8.140556368960468,
+      "grad_norm": 0.7572025060653687,
+      "learning_rate": 1.796875e-05,
+      "loss": 1.0228,
+      "step": 1050
+    },
+    {
+      "epoch": 8.140556368960468,
+      "eval_loss": 1.1517966985702515,
+      "eval_runtime": 11.5429,
+      "eval_samples_per_second": 37.426,
+      "eval_steps_per_second": 18.713,
+      "step": 1050
+    },
+    {
+      "epoch": 8.530990727183992,
+      "grad_norm": 0.6960224509239197,
+      "learning_rate": 1.4062500000000001e-05,
+      "loss": 1.0231,
+      "step": 1100
+    },
+    {
+      "epoch": 8.530990727183992,
+      "eval_loss": 1.108694314956665,
+      "eval_runtime": 11.5162,
+      "eval_samples_per_second": 37.512,
+      "eval_steps_per_second": 18.756,
+      "step": 1100
+    },
+    {
+      "epoch": 8.921425085407517,
+      "grad_norm": 0.6743898391723633,
+      "learning_rate": 1.0156250000000001e-05,
+      "loss": 1.0164,
+      "step": 1150
+    },
+    {
+      "epoch": 8.921425085407517,
+      "eval_loss": 1.1212413311004639,
+      "eval_runtime": 11.5308,
+      "eval_samples_per_second": 37.465,
+      "eval_steps_per_second": 18.732,
+      "step": 1150
     }
   ],
   "logging_steps": 50,
@@ -326,7 +371,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8530543349569946e+17,
+  "total_flos": 3.209686125652214e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null