Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a09e3aa5bd7f4b07f8174215b0b6f89dd110353db1c287e76d5c0af4b3609fe1
+oid sha256:53e28c4620a7451f5adb67bb6c394472c04c6e83810631260f2c339b2ad23837
 size 83946192

last-checkpoint/global_step80/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc12089f97849fa275c57ae3dc6b27e488b6a8784155a15d700d5a30ddaf8836
+size 251686096

last-checkpoint/global_step80/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5698b8bac387395b48771612bd6001813e5729169e2473f4f1cf7c318651d3eb
+size 251686224

last-checkpoint/global_step80/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be26b223b297c996efa99619cf8e1ccc98b9f20493c74eb47c85fc9c278422e8
+size 84231212

last-checkpoint/latest

@@ -1 +1 @@
-global_step60
+global_step80

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2abed2321d91c00781279613ed9e710089d31b08837b217c1ac1f43eabb1f7
+oid sha256:ce0ccc67147a40755f8c851926a02d58c773cf4be69a0da52cbbba3c2d027023
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05a99356747c5972b09bfe0b5a578c25ff9784a6c419c920efc96f409c75a1b
+oid sha256:e819f6ac60b275353b378d437c0706bbb5ab6357ff80d9bf0a965d10ca9b4d2a
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b97ccde9be04c93077654b0c7768345370b9e17ec70913087ac63d4f5b8649f
+oid sha256:85d858de9f2519801a0161b2022aa1dd930b0887f4e61ea82041a687f1ef1276
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.40485483407974243,
-  "best_model_checkpoint": "miner_id_24/checkpoint-60",
-  "epoch": 0.023045899750336087,
+  "best_metric": 0.3683888912200928,
+  "best_model_checkpoint": "miner_id_24/checkpoint-80",
+  "epoch": 0.030727866333781446,
   "eval_steps": 10,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,50 @@
       "eval_samples_per_second": 7.305,
       "eval_steps_per_second": 1.829,
       "step": 60
+    },
+    {
+      "epoch": 0.024966391396197427,
+      "grad_norm": 0.6148959994316101,
+      "learning_rate": 0.0001999835374748198,
+      "loss": 0.4007,
+      "step": 65
+    },
+    {
+      "epoch": 0.026886883042058767,
+      "grad_norm": 0.542120099067688,
+      "learning_rate": 0.0001999796760256485,
+      "loss": 0.331,
+      "step": 70
+    },
+    {
+      "epoch": 0.026886883042058767,
+      "eval_loss": 0.37292301654815674,
+      "eval_runtime": 301.6248,
+      "eval_samples_per_second": 7.271,
+      "eval_steps_per_second": 1.82,
+      "step": 70
+    },
+    {
+      "epoch": 0.028807374687920106,
+      "grad_norm": 0.5689272880554199,
+      "learning_rate": 0.00019997540816597383,
+      "loss": 0.3663,
+      "step": 75
+    },
+    {
+      "epoch": 0.030727866333781446,
+      "grad_norm": 0.3741496801376343,
+      "learning_rate": 0.00019997073391314448,
+      "loss": 0.4308,
+      "step": 80
+    },
+    {
+      "epoch": 0.030727866333781446,
+      "eval_loss": 0.3683888912200928,
+      "eval_runtime": 301.2335,
+      "eval_samples_per_second": 7.28,
+      "eval_steps_per_second": 1.823,
+      "step": 80
     }
   ],
   "logging_steps": 5,
@@ -175,7 +219,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.401392735817564e+17,
+  "total_flos": 4.535190314423419e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null