Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dcd3cc1733beba0d2cfe024b5800ccbcc1ab26ea9926cf8c4f3b88a8198614e
+oid sha256:9f299ed065d076e986e51213d7bf889152797a26591dce7e23c56b2cecc05e88
 size 29034840

last-checkpoint/global_step150/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afea4c76f157e2608c1f997a5ad60002c72ae851b59e9bde62ae07a14d9d80a
+size 43429616

last-checkpoint/global_step150/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52305a9611c890a539013783f0f1598817c011d88270349b046c32183a126dfc
+size 43429616

last-checkpoint/global_step150/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:a844fb8b31d206016bdbf8e85c119d82e6d584dd28c40668d58d6d6c2b324370
+size 43429616

last-checkpoint/global_step150/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2609b1ebf886b70182af89e62775c237894994283827b25c6af3569d1a850da7
+size 43429616

last-checkpoint/global_step150/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f144f33b7ac763950c684990157dad4d1ee523ae43797b9a6b90a998a9d314
+size 637299

last-checkpoint/global_step150/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e0249ea361e86670960dca0ca756a903dbb19568eef1a99e26ae12785a1d69
+size 637171

last-checkpoint/global_step150/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82afbf3944b11f68d9499cbaa773c1fcc29e1a0e9b4eb333a671ffa88a5222fe
+size 637171

last-checkpoint/global_step150/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0caccf9e31a439cb573c5600a0e4625f1ff654d897f43ccfa9da9d8591fe0e
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step100
+global_step150

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+oid sha256:70cc56408014c410353d4dd58ae9b03f4be043f5f800324f66fd8e20e99b840e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+oid sha256:49d1438e98cc9c53a6852464635ce62e9788e61eb3646b73e33813f487c4b6ae
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+oid sha256:4388add9cec90932f8ff0100d27a0574d98e1bad52ff89d44e31967d2b4fbfde
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+oid sha256:a705d6dfaae4f2c1b4b2be6b25a6eb521ffae6fcba21cc1531e97b60037ed079
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e451a9e086b06d7c667be8442b2115f5c088953bade0b625e61f2ce5c7fd404
+oid sha256:c587ef55825cdfdbac47c29c3bd8a2996263c16833a5bd6aaa2fb014bea1e9d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7517351508140564,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-100",
-  "epoch": 0.025753283543651816,
+  "best_metric": 0.7309949994087219,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_stenosis_detect_scale4/lora/sft/checkpoint-150",
+  "epoch": 0.03862992531547772,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -185,11 +185,100 @@
       "eval_steps_per_second": 0.774,
       "num_input_tokens_seen": 1049816,
       "step": 100
+    },
+    {
+      "epoch": 0.027040947720834405,
+      "grad_norm": 0.7251208491150668,
+      "learning_rate": 6.176470588235295e-05,
+      "loss": 0.7579,
+      "num_input_tokens_seen": 1102584,
+      "step": 105
+    },
+    {
+      "epoch": 0.028328611898016998,
+      "grad_norm": 0.8217419839297042,
+      "learning_rate": 6.470588235294118e-05,
+      "loss": 0.7659,
+      "num_input_tokens_seen": 1155512,
+      "step": 110
+    },
+    {
+      "epoch": 0.029616276075199587,
+      "grad_norm": 0.6768053879888967,
+      "learning_rate": 6.764705882352942e-05,
+      "loss": 0.7469,
+      "num_input_tokens_seen": 1207976,
+      "step": 115
+    },
+    {
+      "epoch": 0.03090394025238218,
+      "grad_norm": 1.9562630849642013,
+      "learning_rate": 7.058823529411765e-05,
+      "loss": 0.7353,
+      "num_input_tokens_seen": 1259776,
+      "step": 120
+    },
+    {
+      "epoch": 0.03219160442956477,
+      "grad_norm": 0.6439041597153087,
+      "learning_rate": 7.352941176470589e-05,
+      "loss": 0.7537,
+      "num_input_tokens_seen": 1312760,
+      "step": 125
+    },
+    {
+      "epoch": 0.03347926860674736,
+      "grad_norm": 0.6124318582166212,
+      "learning_rate": 7.647058823529411e-05,
+      "loss": 0.7669,
+      "num_input_tokens_seen": 1365616,
+      "step": 130
+    },
+    {
+      "epoch": 0.03476693278392995,
+      "grad_norm": 0.7593534002488418,
+      "learning_rate": 7.941176470588235e-05,
+      "loss": 0.722,
+      "num_input_tokens_seen": 1417544,
+      "step": 135
+    },
+    {
+      "epoch": 0.036054596961112545,
+      "grad_norm": 0.7827834651032061,
+      "learning_rate": 8.23529411764706e-05,
+      "loss": 0.7502,
+      "num_input_tokens_seen": 1469856,
+      "step": 140
+    },
+    {
+      "epoch": 0.037342261138295134,
+      "grad_norm": 0.5444126155596626,
+      "learning_rate": 8.529411764705883e-05,
+      "loss": 0.7174,
+      "num_input_tokens_seen": 1521496,
+      "step": 145
+    },
+    {
+      "epoch": 0.03862992531547772,
+      "grad_norm": 0.40878703812837747,
+      "learning_rate": 8.823529411764706e-05,
+      "loss": 0.7018,
+      "num_input_tokens_seen": 1573376,
+      "step": 150
+    },
+    {
+      "epoch": 0.03862992531547772,
+      "eval_loss": 0.7309949994087219,
+      "eval_runtime": 38.2005,
+      "eval_samples_per_second": 3.141,
+      "eval_steps_per_second": 0.785,
+      "num_input_tokens_seen": 1573376,
+      "step": 150
     }
   ],
   "logging_steps": 5,
   "max_steps": 3400,
-  "num_input_tokens_seen": 1049816,
+  "num_input_tokens_seen": 1573376,
   "num_train_epochs": 1,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -204,7 +293,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 69233446486016.0,
+  "total_flos": 103777530806272.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null