Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d94e2e3075b4d29e46e5c0b523fa0341f1cfc942214350c627669d578aadac68
+oid sha256:9b7cee3922fcc03ddd02b462320d72e817bf48e4d821bc9bc174cfffb0ecea99
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3972db052ecd4c3f09e208a35dde53cb98f3e8470c87ce17ce263b679cb5575
+oid sha256:68f934757bee3b96c44f1fcd5f66f7c21d6d690ac6920e0836e32f7839398948
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d12ad40cafcf41ebef3793f1bacea211194d01b1709039dcecfc310b37cfe4c8
+oid sha256:913640eb3030e6918a3ab32d574e4ce2a40a5f144929ffe8d31bd7f1b358f50e
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2346f71e8fa54bb462ec3536dd3b00a5d7baa51d353b2a407f22bc20619f73ed
+oid sha256:acd82ba45bf646ef902426ab4e034c595d02ef045ce9b7e0cd2cf700f65691a7
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:648d534e3bfa3788d45747301f1f48cbd9086fc244a9af1c996a30c275d122dc
+oid sha256:cf268cb489a17b00a5da2e7f7b4a75dcc816743c1b54be7c48bf73c90d10ecf4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.76923076923077,
+  "epoch": 12.307692307692308,
   "eval_steps": 40,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,6 +137,28 @@
       "learning_rate": 0.0001821777815225245,
       "loss": 9.7845,
       "step": 140
+    },
+    {
+      "epoch": 11.538461538461538,
+      "grad_norm": 0.361328125,
+      "learning_rate": 0.00017891405093963938,
+      "loss": 9.7359,
+      "step": 150
+    },
+    {
+      "epoch": 12.307692307692308,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00017541066097768963,
+      "loss": 9.688,
+      "step": 160
+    },
+    {
+      "epoch": 12.307692307692308,
+      "eval_loss": 9.67237663269043,
+      "eval_runtime": 5.3075,
+      "eval_samples_per_second": 282.81,
+      "eval_steps_per_second": 4.522,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -156,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 57282196930560.0,
+  "total_flos": 65465367920640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null