Training in progress, step 40, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9159102fedf7a36ab4844c64f693f81ba6bcedebd33d78a4f66f4a8fd78947ad
+oid sha256:bec58c6eccd1fc35a4b9f621263a5eface99a480d472cdd9aec751cc313d500d
 size 4990951248

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:724f905379780e5b1be30d67e4c7f9551f01cfdb17539db0131570d47cec703b
+oid sha256:c2505089526bdc90d3ddb7e176a11cbe2add3a99f8e4757fefeecc51faa1d6bd
 size 559197598

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d608ac51744e2e110b246ac7ce63f62eaebe91057a67a02c54df045b226251
+oid sha256:4977a40e766da6fdc044af7fd59884d4bd214c2ab7ec2ba9b064f45d69b1e14d
 size 5640674860

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5033ef05adedf5e0951c29106132767d6dabb7946365cbb5f31efe4ce4348e
+oid sha256:fa3d855acf1cccac5480ee7b0a805e21db16dd03375e7c77c4579bcbfaae0c9b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bfcb47a14ff29d6b0f9107108175d533a0bdabb46ff0c1e96394b479dc02b7d
+oid sha256:39755c4b29eb55f1c86bc29f4b1fcb6a7c6eb4692c79b864c7747cd912a7c46e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b6004d08eec141d8acdc89d661c25984f92dce53cfafa95e9b8e547363322f5
+oid sha256:2a2c836bb64fba5c8b5980803f06f2b361f91cd73fe399d8a19a2c8b1e3c07d0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:653a6d9f4a511b13bcc437cd74aaba23de59482cbb30c65709a3378d8d7664a2
+oid sha256:334cf1d776bffd3c870e2c3d5e5dac0a97f280b4a09e897269512850944cd189
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a562280f18454416a11d2a32a1435679f44d10b11637c5297815c06d499163
+oid sha256:9248d7f262b73b7b212e6bf7f6f66a12efea2182db378d6a810b44dc89e3400f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6451612903225806,
+  "epoch": 1.2903225806451613,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 73.214,
       "eval_steps_per_second": 3.073,
       "step": 20
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 8.9375,
+      "learning_rate": 0.00019994532573409262,
+      "loss": 2.3976,
+      "step": 30
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 9.875,
+      "learning_rate": 0.00019950829025450114,
+      "loss": 2.4629,
+      "step": 40
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "eval_loss": 2.5420961380004883,
+      "eval_runtime": 20.3055,
+      "eval_samples_per_second": 73.921,
+      "eval_steps_per_second": 3.103,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5608478089347072e+16,
+  "total_flos": 3.1184438444425216e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null