Training in progress, step 1500, checkpoint

last-checkpoint/global_step1500/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad45807b213eb148d0bdcbc685c255f57eeaafd1adf4fa191e60aebec46e8742
+size 77125

last-checkpoint/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a9529806b74369e61ae304c3d3053fd0187f1bc4e986ca2dcc7f1fc9afd449
+size 181523565

last-checkpoint/global_step1500/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396a26d95b53e4e5870eae98798d41db844210f38e705aed71ea34c9b6f84cf8
+size 76997

last-checkpoint/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4b938d275f542c62dc6288898a7b28064ed43540f5f8dc2a06d1aac6e03c45
+size 181523565

last-checkpoint/global_step1500/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26a8bd5b3b5268efb898fe728303d908983623e05d8e6c3cec43982cf12bafa5
+size 76997

last-checkpoint/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8c00e46c3bc4c0821ea7b20b84073c03bfa324cb710027303657f7a06b0d0b
+size 181523565

last-checkpoint/global_step1500/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62334d958c423aa318ab2649fc7949e8fee64bc7ab618ac1403aa296b2f74fdd
+size 76997

last-checkpoint/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12c10faf7f0180ab70dd51abc957a2dbda112ba269a717d8d027b5569120eef2
+size 181523565

last-checkpoint/latest

@@ -1 +1 @@
-global_step1000
+global_step1500

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c2bbd8242bb5c02d5efae94f8f42fb03edd2c72266a812ab965e463320da46
+oid sha256:194af0302478c97171645454a5eb846b0fc5f8e392d4e3959fa03596fc8e4026
 size 242070038

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dce2c50c7664fbb16a8b2e43e54b53331c5316cfb271b983da1e5fecb8f17cbd
+oid sha256:6d3cf537aeb636d74260ac33f9ee9f5f5488cd868e57c67412d317e90d714583
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0840849d39e1eaa57787311e4d0c83224a6ddc9e6a9cb14192c8ed84be6eab9
+oid sha256:f46e6b131c11a49aaf40dd0567abef518102c7a1352bb71be9e97f08d2acdd07
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eab21c7407cea42cd27eaeed6921c9d828e73c23bb9f05f571d16961ccadac8
+oid sha256:af26ea8cc81928ae6c96810dd49af32aaee79970eeeea540d94edd0eded31879
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa9b8022f28fa939456417d280e7aafb2c4ebe7a3815d932c02df2e413189df
+oid sha256:28da90f216354525bfc6e2c4fb7d9537e9448788220df6cdda43e8d5ba71d985
 size 15024

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.0,
+  "epoch": 6.0,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -19,13 +19,19 @@
       "learning_rate": 0.01,
       "loss": 0.1287,
       "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.01,
+      "loss": 0.1689,
+      "step": 1500
     }
   ],
   "logging_steps": 500,
   "max_steps": 2500,
   "num_train_epochs": 10,
   "save_steps": 500,
-  "total_flos": 169032155136.0,
+  "total_flos": 253548232704.0,
   "trial_name": null,
   "trial_params": null
 }