Training in progress, step 60, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec58c6eccd1fc35a4b9f621263a5eface99a480d472cdd9aec751cc313d500d
+oid sha256:25c857ff19b5adf50a631790577a8b8f083a3e860d43c11647116022c57f2400
 size 4990951248

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2505089526bdc90d3ddb7e176a11cbe2add3a99f8e4757fefeecc51faa1d6bd
+oid sha256:ea117d3be8b7f606e8f0df9669b9674cc0c177a3f41530fb4b49852d281cf709
 size 559197598

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4977a40e766da6fdc044af7fd59884d4bd214c2ab7ec2ba9b064f45d69b1e14d
+oid sha256:4a5d994bd5a403db564d2e586df727af1e1a8965b708a077ea1ebf9d3b171c7d
 size 5640674860

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa3d855acf1cccac5480ee7b0a805e21db16dd03375e7c77c4579bcbfaae0c9b
+oid sha256:ee79d800c9a2e264a65d6a3737f4962e778c9d7f80d6768b8edca0eab21c8a92
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39755c4b29eb55f1c86bc29f4b1fcb6a7c6eb4692c79b864c7747cd912a7c46e
+oid sha256:7bca44b3406787bbe774f3a29ce0829dfb77a865b68b27b9e43acbe4e5eed16c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a2c836bb64fba5c8b5980803f06f2b361f91cd73fe399d8a19a2c8b1e3c07d0
+oid sha256:00c4501abe63013597d8ae9d4d94b5d2a3244495e565f60cd63e4d4ed904ecf9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334cf1d776bffd3c870e2c3d5e5dac0a97f280b4a09e897269512850944cd189
+oid sha256:d38c27a3df45459b9e8441485927824c74e0caf5211147ff5b4d04031c0e3ce9
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9248d7f262b73b7b212e6bf7f6f66a12efea2182db378d6a810b44dc89e3400f
+oid sha256:73474ac15ab1f9e7ff2dbea9beffe9a6867347710a3cf2ee966c6a4a98243bef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2903225806451613,
+  "epoch": 1.935483870967742,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 73.921,
       "eval_steps_per_second": 3.103,
       "step": 40
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 3.9375,
+      "learning_rate": 0.00019863613034027224,
+      "loss": 2.6415,
+      "step": 50
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 76.5,
+      "learning_rate": 0.0001973326597248006,
+      "loss": 3.0008,
+      "step": 60
+    },
+    {
+      "epoch": 1.935483870967742,
+      "eval_loss": 2.800191879272461,
+      "eval_runtime": 20.2683,
+      "eval_samples_per_second": 74.057,
+      "eval_steps_per_second": 3.108,
+      "step": 60
     }
   ],
   "logging_steps": 10,
@@ -78,7 +100,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1184438444425216e+16,
+  "total_flos": 4.679291653377229e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null