Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69e5b496c36ad259db37344eb706b381e79be34b12a26861d7f318295dcfd58
+oid sha256:60c80d389637b5f5cae317955ea9368ed58131fb66260b7e896c23b167e9cf7b
 size 29034840

last-checkpoint/global_step1200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b1be5e541d7054f593eb5336f07144b4c45a392caa51e3f89f3b9a4039b25e1
+size 43429616

last-checkpoint/global_step1200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47da22d2e76ec4ef4c272a509f43a0f8b566ae69ed73e32b131ff13d81209f0a
+size 43429616

last-checkpoint/global_step1200/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:e0d8cd6478436876aace2da6ad611707eedbe138391f26d8840dbc1e9f67a653
+size 43429616

last-checkpoint/global_step1200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4927440aed262ba80b9104518087387cc6a40c362c4e4c3a5b6aed1dee2afd29
+size 43429616

last-checkpoint/global_step1200/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d06f5911185a6ebb03a50cfa88a0b397d7dcb732800b879d25a0b602da1df67
+size 637299

last-checkpoint/global_step1200/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ddb6eccf101a9bfdd7a0e209ad8e34c5bd436c139a6cc24e86858cfb663649f
+size 637171

last-checkpoint/global_step1200/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63fa0ba1e22cd4330a732b53b080494fee16b561a8509fb226cb0abdd186e7ea
+size 637171

last-checkpoint/global_step1200/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a54361c50a0229f80835738434c247594a5157c91a95390f6abdef0e295dfb9d
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step1150
+global_step1200

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274dc3860ee0c7f4d5348f60910a4b568498c04adfefb89f905b1c78a82c1312
+oid sha256:a209a0c0025f9ce8e2beeba50c1f0828d5c34a2482310fcd0bf5fc24c2c67be2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9aa441491b9ca89e796944520fa1db332a67c0a1a920be83edd2d96d741716d
+oid sha256:a67fb929b8c51f9b1c6ff9f11366e57e55128a1d36df85a9d37a008b49017a75
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ee3434533b24fb771504fa8cceb5c2ea25fe0de1641128feaceccc65afe6ed
+oid sha256:1b9ef3b0c0978d0b611f4257c939f1c2c6f07e6227bfea6675532d285b0b64a7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93b4a44be1335173d2e3120bd0d1e6346f3e832d8935752c70ce1e98f017fa87
+oid sha256:0183d14c8ed52ee533139532e9bcf7bc34ec297a064845b35741cb501d92675f
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc7c1c90680adb84a90114a256d228473c266c4da4454cc4d39e70f828ce64ad
+oid sha256:17a5556c8233d79e1be6279770d5e53a5fee5448790e76942f098adafb906464
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.42494550347328186,
-  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-1150",
-  "epoch": 0.3397341211225997,
+  "best_metric": 0.2966395914554596,
+  "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-1200",
+  "epoch": 0.35450516986706054,
   "eval_steps": 50,
-  "global_step": 1150,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2054,11 +2054,100 @@
       "eval_steps_per_second": 0.765,
       "num_input_tokens_seen": 11933632,
       "step": 1150
+    },
+    {
+      "epoch": 0.3412112259970458,
+      "grad_norm": 4.778973114307738,
+      "learning_rate": 9.60798322936489e-05,
+      "loss": 0.3716,
+      "num_input_tokens_seen": 11986496,
+      "step": 1155
+    },
+    {
+      "epoch": 0.34268833087149186,
+      "grad_norm": 8.20796735033587,
+      "learning_rate": 9.603229145032993e-05,
+      "loss": 0.4234,
+      "num_input_tokens_seen": 12039112,
+      "step": 1160
+    },
+    {
+      "epoch": 0.34416543574593794,
+      "grad_norm": 7.158508103350641,
+      "learning_rate": 9.598447597882181e-05,
+      "loss": 0.3973,
+      "num_input_tokens_seen": 12091728,
+      "step": 1165
+    },
+    {
+      "epoch": 0.345642540620384,
+      "grad_norm": 9.320131732384727,
+      "learning_rate": 9.593638616439118e-05,
+      "loss": 0.3494,
+      "num_input_tokens_seen": 12143896,
+      "step": 1170
+    },
+    {
+      "epoch": 0.34711964549483015,
+      "grad_norm": 10.150141046652656,
+      "learning_rate": 9.588802229394137e-05,
+      "loss": 0.4182,
+      "num_input_tokens_seen": 12195336,
+      "step": 1175
+    },
+    {
+      "epoch": 0.34859675036927623,
+      "grad_norm": 9.270011962927722,
+      "learning_rate": 9.583938465601075e-05,
+      "loss": 0.462,
+      "num_input_tokens_seen": 12247696,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3500738552437223,
+      "grad_norm": 8.96068778293971,
+      "learning_rate": 9.5790473540771e-05,
+      "loss": 0.4451,
+      "num_input_tokens_seen": 12300040,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3515509601181684,
+      "grad_norm": 24.761476817148992,
+      "learning_rate": 9.574128924002533e-05,
+      "loss": 0.4789,
+      "num_input_tokens_seen": 12351904,
+      "step": 1190
+    },
+    {
+      "epoch": 0.35302806499261447,
+      "grad_norm": 1.8519516556186366,
+      "learning_rate": 9.569183204720677e-05,
+      "loss": 0.3898,
+      "num_input_tokens_seen": 12403280,
+      "step": 1195
+    },
+    {
+      "epoch": 0.35450516986706054,
+      "grad_norm": 5.005586803143539,
+      "learning_rate": 9.564210225737647e-05,
+      "loss": 0.3296,
+      "num_input_tokens_seen": 12456040,
+      "step": 1200
+    },
+    {
+      "epoch": 0.35450516986706054,
+      "eval_loss": 0.2966395914554596,
+      "eval_runtime": 19.5244,
+      "eval_samples_per_second": 3.073,
+      "eval_steps_per_second": 0.768,
+      "num_input_tokens_seen": 12456040,
+      "step": 1200
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 11933632,
+  "num_input_tokens_seen": 12456040,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -2073,7 +2162,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 787259637891072.0,
+  "total_flos": 821733054480384.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null