Training in progress, step 404, checkpoint

last-checkpoint/optimizer_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795b7f6b14618c8d2f3126c050c747db33847a0d58bd5aee9fd555d8072054d4
+oid sha256:fb2d3438714bb9940d9a8e27d551ef3f3e8ec8e59de54106a3f9386436f9afc2
 size 13934748

last-checkpoint/optimizer_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca055109122571586c2a64df4ff7cbfe48d022bc8722566c0895ac272edc3c78
+oid sha256:bb83eab302f9357f0a1b90889673cb5993b1c3a3e82192cb72e581582913bb6d
 size 13999412

last-checkpoint/optimizer_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86c3c549ce130a9ab4d45068f1c63e35984edd9e565e1205374afe3fd1bd9f49
+oid sha256:e9404976e4e6d288b71cf6c5bfcea47b340bc240e85feee20888b2de352c5d0b
 size 13990904

last-checkpoint/optimizer_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b1101f8377361468d680d48119c20867c8d300a96337536353857f42fd2abf3
+oid sha256:5e8da75076d5d193bad087a5ce5c0fb4966374584b64be545c58cb9481edb593
 size 13990904

last-checkpoint/pytorch_model_fsdp_0/__0_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9eeccce1ea7069a8e741721cfd0ff7753c42789e7631b2bb13751b0262b8471
+oid sha256:a111d23d0f1139631ca4e2a08709add794b4fb928a7ae4d43e7b6f2d5494c74e
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__1_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d3c3983e0244f589f3c97391149136519c0ae2cb30573bc57afef1b7fecaa9
+oid sha256:fd739a6d541d8696ae2c74903d11e72df4fbfb0efc87e368250ea67b913f2368
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__2_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3cccf70ced1d6c40e4cd73d50ab8d98ca34680aa33a692208ccd7e3f14b89ff
+oid sha256:4ba4531b3bb3e4263cc9eda2d3d48909cc82e0bb23b4ee4a19aa9ce727eadad0
 size 6966784

last-checkpoint/pytorch_model_fsdp_0/__3_0.distcp

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e67188121d44320e3e4446d495eac2f4a44fb1b8839c93a496a50e5e6ce242b
+oid sha256:5816255bf7351b8dac53ac9afb64b32c061783e0a39d9bbd54397845a6649257
 size 6966784

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48a7b3dc91adc39858108306f7d4532b1fd3e6514365ab372dc62dfd9ee10e2
+oid sha256:51798a6a0b577d24b776621cf87e86548de5d4500f4e1a24f260f2d387f5f292
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be021af7b36e06a7835029caab84a249be037bdd789560931d603f08da17b1cf
+oid sha256:c7f625ef1a452a24efa4cbeb511066f9331fc4303f62d5be623bf75f40f304a5
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b4a02e9af72c5cebb6c447096e61f1d87135b21700c6e8b096a268a56e20c67
+oid sha256:7f018ed359ff78502a1a99fa089004babbae93c67466eb5956f7788d986c65f6
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3549f26e113bbe422032c22e335cbabac24ad3593e9e3e43ecfa59c401538f39
+oid sha256:36100e53e523d76076470698e16abf1c1eb3456412f7169c245d73dc7ca653c0
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4910675856682caf109c9ff6535f1bae50ae0cf757d7603f89fd4ad22523009c
+oid sha256:325691efe1203aa44eb00f78b4e2bbfa6cc3ed363b6560f2be782e55022c6921
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9900990099009901,
+  "epoch": 1.0,
   "eval_steps": 20,
-  "global_step": 400,
+  "global_step": 404,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3059,6 +3059,34 @@
       "eval_samples_per_second": 5.747,
       "eval_steps_per_second": 0.187,
       "step": 400
+    },
+    {
+      "epoch": 0.9925742574257426,
+      "grad_norm": 3.1237950325012207,
+      "learning_rate": 3.3703469648760367e-09,
+      "loss": 0.1846,
+      "step": 401
+    },
+    {
+      "epoch": 0.995049504950495,
+      "grad_norm": 2.9061472415924072,
+      "learning_rate": 1.497978733961958e-09,
+      "loss": 0.1893,
+      "step": 402
+    },
+    {
+      "epoch": 0.9975247524752475,
+      "grad_norm": 2.3139050006866455,
+      "learning_rate": 3.745016960665648e-10,
+      "loss": 0.2027,
+      "step": 403
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.076274871826172,
+      "learning_rate": 0.0,
+      "loss": 0.1372,
+      "step": 404
     }
   ],
   "logging_steps": 1,
@@ -3073,12 +3101,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.454079047550894e+17,
+  "total_flos": 2.478660532526121e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null