Training in progress, step 150, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c15a34ec1b4d3d4fbaeb960fd708de5db3f303c2b549df51725295172d1360c
+oid sha256:e07b0d5cb25af720f71383ccc930a376f4e2d90d2f9691e717bb1bfc622e6c29
 size 4972163696

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7544d672f19439e82165eb8bf76e30fd101a87ec3778efd94e86e2741d0051f
+oid sha256:47d57fa3d174addd4ea8b84f78c18b0975d6b8244b9f509ee5c031ae9437d0a9
 size 2669366920

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2590f9284e12a5bae29178a457254993014e58377b152f8d15234dfd81a13f59
+oid sha256:444b9d82ed3ff7841cdbd49d67d42846aeea68af34ecad413a17f727dc6ba26c
 size 7762295162

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f105b50093489fd740a8f6602ddfe873d388d5a0db4242d627bbb8ba93713d73
+oid sha256:bd0b45e6fd019f23318ffd2d46ef8cf6d2a160038f49f06fc17960b67863906f
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac67ce68566e593180659981e408823cfcf7642579fefd1cbac723e565bb9c8
+oid sha256:9e71e2096e47d5825ef2ce323a1cf303b37363e73043bd284a3ba35f73c6da6e
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b138c732cb9c881cb2fed2b16c2fccdaaf3f697d85bd2ae2853572bd36b881f
+oid sha256:220a99772b3d8f35e3e108e580fbc19089c4a43d7f11750324b648fbd4e2c7d7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9433962264150944,
+  "epoch": 1.4150943396226414,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 39.451,
       "eval_steps_per_second": 4.941,
       "step": 100
+    },
+    {
+      "epoch": 1.0377358490566038,
+      "grad_norm": 1.6875,
+      "learning_rate": 0.00019934553477549794,
+      "loss": 1.5189,
+      "step": 110
+    },
+    {
+      "epoch": 1.1320754716981132,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.0001990228692687429,
+      "loss": 1.117,
+      "step": 120
+    },
+    {
+      "epoch": 1.2264150943396226,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 1.3558,
+      "step": 130
+    },
+    {
+      "epoch": 1.320754716981132,
+      "grad_norm": 1.1484375,
+      "learning_rate": 0.00019818556823214268,
+      "loss": 1.1093,
+      "step": 140
+    },
+    {
+      "epoch": 1.4150943396226414,
+      "grad_norm": 1.109375,
+      "learning_rate": 0.00019767147448363366,
+      "loss": 1.0954,
+      "step": 150
+    },
+    {
+      "epoch": 1.4150943396226414,
+      "eval_loss": 1.7661364078521729,
+      "eval_runtime": 37.4546,
+      "eval_samples_per_second": 40.075,
+      "eval_steps_per_second": 5.019,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.65928395046912e+16,
+  "total_flos": 5.484351812376986e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null