Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92c3ca36e9dd4d11ab85588a56c6fb7b33a51db0bfd3d4eb3ee825accee6a828
+oid sha256:e07bb356c3c42e5cdc07d10d2311f6b5d583b9c0243d40576869a8a8468b6d98
 size 80014016

last-checkpoint/global_step120/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66dc06d93f59c002bd6980986bbd53dab716b8588332f09e290885a539e536f3
+size 60296272

last-checkpoint/global_step120/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:274b6848025365e3dda92951d0ca3e5d15f264a98269a8c215418b1e6630f50c
+size 60296400

last-checkpoint/global_step120/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92415e1541c796ef60a91fd9fc6f046a75c96bd56685c357cc821aba8e9ad88
+size 60296400

last-checkpoint/global_step120/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42e7578deced32b54388e031ab71404067972e3c7e6413672d16489b6bb4b9cb
+size 60296400

last-checkpoint/global_step120/mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0051d479ecabaf7850bc6a78ce63326f1ec673808c117ceaae6b5af296aa15b8
+size 80296428

last-checkpoint/latest

@@ -1 +1 @@
-global_step80
+global_step120

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5140c0994a4009e2bd1bdabfcc4d1ef6e2398fa905a081db9641fd12a8aef58e
+oid sha256:ca446724d1ebce77ccae7f35340aabb59e5bca2ba79e103237fd5f8b74b534ac
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c9018248062ac40731f8f160cde9bcf648a19dc4d6c04ac8c07a5ac8dbc63ab
+oid sha256:72284f3bf1ea5778c38096c11524890c08f7bd83e9ef49537cb678a37a80dc25
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7138d4e5f63e17a11068cd327d0123256938b5c0ac9100060f799e1689debf24
+oid sha256:4a8554acf33597a260ef009c9e86cc0718a7640fdf53a7e753811647743bf70a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03cc86f7684c1db139e3ec7994865b6ab0ab40f5a57ca5af414e11cc912dd03b
+oid sha256:5b0f0993e706c9ca5d8f708ef0f01e07d0edb3dd3e3db326b06ad6f26f3cf62c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c74ea4c289ec2b8f9336a171496a3ab2f72be98f2c877ad703552d865f9922
+oid sha256:31d2e54503626585fe3bd1382687ba707fdc17dcc88507487c697e511203f899
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 80,
-  "best_metric": 1.1793321371078491,
-  "best_model_checkpoint": "miner_id_24/checkpoint-80",
-  "epoch": 0.6584362139917695,
+  "best_global_step": 120,
+  "best_metric": 1.1266472339630127,
+  "best_model_checkpoint": "miner_id_24/checkpoint-120",
+  "epoch": 0.9876543209876543,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,78 @@
       "eval_samples_per_second": 14.47,
       "eval_steps_per_second": 0.907,
       "step": 80
+    },
+    {
+      "epoch": 0.6995884773662552,
+      "grad_norm": 0.06558868288993835,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 1.1719,
+      "step": 85
+    },
+    {
+      "epoch": 0.7407407407407407,
+      "grad_norm": 0.06846272945404053,
+      "learning_rate": 0.00011866666666666669,
+      "loss": 1.1555,
+      "step": 90
+    },
+    {
+      "epoch": 0.7818930041152263,
+      "grad_norm": 0.07038144767284393,
+      "learning_rate": 0.00012533333333333334,
+      "loss": 1.1683,
+      "step": 95
+    },
+    {
+      "epoch": 0.823045267489712,
+      "grad_norm": 0.07254977524280548,
+      "learning_rate": 0.000132,
+      "loss": 1.1592,
+      "step": 100
+    },
+    {
+      "epoch": 0.823045267489712,
+      "eval_loss": 1.148273229598999,
+      "eval_runtime": 274.3966,
+      "eval_samples_per_second": 14.413,
+      "eval_steps_per_second": 0.904,
+      "step": 100
+    },
+    {
+      "epoch": 0.8641975308641975,
+      "grad_norm": 0.07729992270469666,
+      "learning_rate": 0.00013866666666666669,
+      "loss": 1.1482,
+      "step": 105
+    },
+    {
+      "epoch": 0.9053497942386831,
+      "grad_norm": 0.08038458973169327,
+      "learning_rate": 0.00014533333333333333,
+      "loss": 1.1458,
+      "step": 110
+    },
+    {
+      "epoch": 0.9465020576131687,
+      "grad_norm": 0.08932825922966003,
+      "learning_rate": 0.000152,
+      "loss": 1.1384,
+      "step": 115
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "grad_norm": 0.08660374581813812,
+      "learning_rate": 0.00015866666666666668,
+      "loss": 1.129,
+      "step": 120
+    },
+    {
+      "epoch": 0.9876543209876543,
+      "eval_loss": 1.1266472339630127,
+      "eval_runtime": 272.2952,
+      "eval_samples_per_second": 14.525,
+      "eval_steps_per_second": 0.911,
+      "step": 120
     }
   ],
   "logging_steps": 5,
@@ -188,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6728695582658396e+18,
+  "total_flos": 2.5093043373987594e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null